CN110110008A - A kind of shared motivational techniques of the block chain medical data based on Charolais cattle - Google Patents
A kind of shared motivational techniques of the block chain medical data based on Charolais cattle Download PDFInfo
- Publication number
- CN110110008A CN110110008A CN201910379542.7A CN201910379542A CN110110008A CN 110110008 A CN110110008 A CN 110110008A CN 201910379542 A CN201910379542 A CN 201910379542A CN 110110008 A CN110110008 A CN 110110008A
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- shared
- medical data
- owner
- 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
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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to a kind of, and the block chain medical data based on Charolais cattle shares motivational techniques, belongs to block chain network applied technical field.Motivational techniques are shared by establishing block chain medical data, alliance's income is allocated using Shapley value method between cooperative alliances member, the inspiration problem that medical data is shared under block chain application scenarios is solved, the block chain medical data of proposition, which shares motivational techniques, can effectively motivate cooperative alliances member to participate in cooperation and shared truthful data.The method considers the weight of all members in the percentage contribution and cooperative alliances of data owner, so that the income distribution program based on Shapley value method is suitable for the medical data with percentage contribution difference and shares scene;It is the reward mechanism of the common recognition node formulation justice in alliance's chain network for the practical Byzantine failure tolerance algorithm characteristics for being applied to alliance's chain.
Description
Technical field
The present invention relates to a kind of, and the block chain medical data based on Charolais cattle shares motivational techniques, it is intended to block chain field
Participant's contribution under scape in data sharing cooperation is assessed, and realizes the reasonable distribution of cooperation benefit, excitation associated user's product
Pole participates in cooperating and executes standard operation, belongs to block chain network applied technical field.
Background technique
Along with the development of information technology, health care industry has more and more wide development space, electronic medical records
(Electronic Medical Record, EMR) become medical information data product, mass data patient see a doctor, face
Bed is seen a doctor, is generated during wearable device, and realizes the information system management to medical data by EMR.It is cured by combining
Big data and artificial intelligence are treated, science diagnosis and the patient's pathological analysis of a variety of diseases may be implemented, it is accurate to improve medical diagnosis
Rate and efficiency, and the workload amount of doctor is reduced, auxiliary doctor carries out lesion detection, realizes disease early screening.However, medical
Big data is faced with numerous challenges in development, and all there is urgently in the storage of data, the shared and monitoring of data source
It solves the problems, such as.The appearance of the emerging technologies such as block chain is that health care industry brings new opportunity.
Block chain technique functions are just applied to the electronic-monetary systems such as bit coin, have decentralization, go trustization, can chase after
Track such as can not distort at the characteristics, make medical data management without relying on the third-party institution, and be data integrity, data tracing
And market surpervision provides powerful guarantee.Strict access control is carried out to data using block chain, guarantees that the data of user are hidden
Private is inviolable, while can be realized effective pipe that a large amount of medical datas of numerous hospitals or medical institutions are stored in dispersion
Reason saves the expense for safeguarding the processes such as complete medical records, monitoring data source, provides safeguard for the public trust of system.Area
Block chain medical treatment has been subjected to the extensive concern of researcher.
Currently, the block chain application study in medical data project is controlled mainly for data access and data security protecting
The problems such as, have certain theoretical basis.Although block chain technology has important value, relevant item quantity in medical field
Rapid growth, but there is also many problems to restrict the development of industry at present, for the landing of block chain medical item, also
Very long stretch will be walked.By being shared to medical data, it can more fully play and be deposited in the dispersion of each medical institutions
The value of the medical data of storage finally converts potential knowledge, such as the patient history that research institution can will acquire for data
Data are for modeling and machine learning and carry out adjuvant treatment and health consultation.The research institution of data analysis is carried out as number
Data value can be played by cooperation according to requestor and data owner, and made a profit by providing medical services.But general feelings
Under condition, data owner is reluctant to provide data, and to share the behavior of medical data must be paid, therefore is only centainly rewarding
The shared cooperation of medical data can just be facilitated under encouragement.Data value how is measured, data trade rule how is formulated, is gathered around for data
The person's of having payt is that block chain must be solved the problems, such as in medical field landing.Therefore, it is necessary to use reasonable excitation side
Method promotes data sharing both sides to reach the cooperation of block chain medical item, to form a kind of business mould for meeting market rules
Formula.In view of the above problems, the motivational techniques that this method research block chain medical data is shared, the process shared according to medical data
It is medical under block platform chain to solve using a kind of Research of Cooperative Game algorithm based on contribution, i.e. Shapley value method with feature
Alliance's Income Distribution Problem of data sharing cooperation designs a kind of shared motivational techniques of effective medical data.
Summary of the invention
It is an object of the invention to solve existing block chain medical data to share inspiration problem, propose a kind of based on Sharp
The block chain medical data of benefit value shares motivational techniques, is allocated, realizes to the income generated in the shared cooperation of medical data
To the Persistent Excitation of cooperation allied member, and then promote the shared cooperation of medical data.
The core idea of the invention is as follows: it establishes block chain medical data and shares incentive mechanism, between cooperative alliances member
Alliance's income is allocated using Shapley value method, solves the inspiration problem that medical data is shared under block chain application scenarios,
Distribution of income considers the weight of all members in the percentage contribution and cooperative alliances of data owner, the block chain medical treatment of foundation
Data sharing incentive mechanism can effectively motivate cooperative alliances member to participate in cooperating and sharing truthful data, propose one kind and be based on
The block chain medical data of Charolais cattle shares motivational techniques.
A kind of shared cooperation of medical data that the shared motivational techniques of the block chain medical data based on Charolais cattle are relied on
It include that medical data shares cooperative alliances in modelMedical data and using medical data provide medical services and generate
Income.
Wherein, medical data shares cooperative alliancesIt is data requester setCommon recognition node collection
It closesGather with data ownerAnd, i.e.,
ForThe number of middle data requester,ForThe number of middle common recognition node,ForThe number of middle data owner;Doctor
Treat data sharing cooperative alliancesIn all cooperative alliances members alliance's catenary system based on practical Byzantine failure tolerance algorithm into
It practises medicine and treats data sharing;Alliance's chain based on practical Byzantine failure tolerance algorithm is that a kind of cooperative alliances number of members is controllable and have
The block chain of high serious forgiveness, is made of the block of sustainable growth, and shared medical data information is recorded in by generating block
On block chain, during generating block it is all with it is final common recognition reach an agreement response common recognition node be normal node;
Wherein, the type collection of medical data is combined into Element in set represents medical data kind
The code name of class;The type of medical data isKind, andKind medical data is gathered by data ownerWith data requester
SetIt is shared;Medical data and medical data share cooperative alliancesRelationship specifically: data owner setMiddle jth
A data owner HjShared data class set expression is Pj, data requester setIn i-th of data requester TiPlease
The data class set expression asked is Ri, set PjWith set RiIt is setSubset, i.e.,J is more than or equal to 1
And it is less than or equal toI is more than or equal to 1 and is less than or equal toData owner HjThe data sharing that type is d is asked to data
The person of asking TiIt indicates are as follows: d ∈ PjAnd d ∈ Ri;D is medical data type setIn an element, i.e.,
Wherein, the income for providing medical services using medical data and generating is usedIt indicates;Meaning asked for data
The person of asking TiThe income for providing medical services by using type for the data of d and generating;
The block chain medical data shares motivational techniques, includes the following steps:
Step 1 gathers data ownerDivide and using medical data building test set, training prediction mould
Type, then F1- index is calculated, specifically:
The data class that step 1.1 is shared according to all data owners, data owner is gatheredIt is divided intoIt is a
Subclass
Step 1.2 is shared in cooperative model according to medical dataA medical data type, buildingA test set,
Each test set is made of several samples with label,The data class of a test set is shared with medical data respectively to be closed
Make in modelKind medical data type is identical;
The medical data building training set and training prediction mould of data owner's set h ' shared d type of step 1.3
Type, tests prediction model and statistical forecast as a result, calculate the F1- index of prediction model again;
Wherein, h ' is the set of data owner's composition of shared d type data,
Wherein, hdThe set formed for the data owner of all shared d type data;
Step 1.3 specifically includes following sub-step again:
The data for the d type that step 1.3A is shared using all data owners in data owner's set h ' construct training
Collection;
Step 1.3B utilizes prediction model of the training set data training based on support vector machines;
The test set that step 1.3C is d using the data class constructed in step 1.2, the prediction to being established in step 1.3B
Model is tested, and obtains the prediction result of all samples in test set, compares the label of prediction result and sample, statistics TP,
The numerical value of tetra- prediction results of TN, FP and FN;
Wherein, TP indicates the quantity of class that the prediction of positive class is positive;TN indicates the quantity of class that the prediction of negative class is negative;FP is indicated
Negative class is predicted into the class that is positive, that is, the quantity reported by mistake, FN indicates class that the prediction of positive class is negative, that is, the quantity failed to report;
Step 1.3D calculates the F1- index of prediction model by formula (1):
Wherein, F1 (h ') is using the F1- index of the prediction model for the data training shared in h ', and P is prediction model
Accuracy rate, R are the recall rate of prediction model, are calculated respectively by formula (2) and formula (3):
Step 2 calculates data owner H by formula (4)jContributrion margin in shared d type data
Wherein, Hj∈hd, For data owner's setRemove HjRemaining all data are gathered around afterwards
The set being made of person,Meaning be data owner HjData owner is gathered on F1- index's
Contributrion margin, i.e. HjCoalize the difference of front and back F1- change index;
Wherein,For hdAll subsets in include data owner HjSubset composed by set;
Step 3 calculates common recognition node M by formula (5)kIncome account for the ratio P of all common recognition the sum of nodes revenuesk:
Wherein, k is more than or equal to 1 and is less than or equal to It indicatesThe quantity of middle common recognition node, PkExpression is distributed to
Common recognition node MkIncome account for setIn it is all common recognition node total revenues ratio, n be medical data shared procedure in generate
Block quantity, AkFor node M of knowing togetherkSet composed by the serial number of all blocks generated when as normal node, i.e.,qiFor the quantity when generating the block of serial number i as the common recognition node of normal node, pass through formula
(6) it calculates:
Wherein, I is set, i.e. I={ 1 ..., n } composed by the serial number of all blocks;
Step 4 utilizes Shapley value method, the shared cooperative alliances of calculating medical dataIn all members income, pass through
Formula (7), formula (8) and formula (9) calculate separately data owner HjIncomeCommon recognition node MkIncomeSum number
According to requestor TiIncome
Wherein,It is calculated respectively by formula (10), formula (11) and formula (12):
Wherein,For data owner's set hd, common recognition node setWith data requester set { TiAnd, i.e., For setThe quantity of middle data owner, w (x) are the set that allied member's quantity is x
Weighting function, calculated by formula (13):
Beneficial effect
A kind of block chain medical data based on Charolais cattle proposed by the present invention shares motivational techniques, and block chain is cured
The landing for the treatment of, has the advantages that
(1) the shared excitation of the medical data that the present invention is suitable for carrying out under block chain environment;
(2) present invention considers the weight of all members in the percentage contribution and cooperative alliances of data owner, makes to be based on
The income distribution program of Shapley value method is suitable for the medical data with percentage contribution difference and shares scene;
(3) present invention is the common recognition section in alliance's chain network for the Byzantine failure tolerance algorithm characteristics applied to alliance's chain
Point formulates fair reward mechanism;
(4) present invention is proved by mass data, it is shared to block chain medical data in cooperative alliances member carry out
Distribution of income can motivate the shared cooperation of block chain medical data.
Detailed description of the invention
Fig. 1 is that a kind of block chain medical data based on Charolais cattle of the present invention shares the medical number that motivational techniques are relied on
According to shared cooperative model;
Fig. 2 is data owner's number that a kind of block chain medical data based on Charolais cattle of the present invention shares motivational techniques
Amount-distribution of income result relation schematic diagram.
Specific embodiment
With reference to the accompanying drawings and examples, " a kind of block chain medical data based on Charolais cattle of the invention is illustrated
The process of shared motivational techniques ", and illustrate its advantage.It should be pointed out that implementation of the invention is not limited to following embodiment, to this hair
The bright accommodation made in any form or change will fall into the scope of the present invention.
Embodiment 1
The present embodiment establish a kind of block chain medical data based on Charolais cattle of the present invention share motivational techniques institute according to
The medical data of support shares cooperative model, as shown in Figure 1.
Fig. 1 describes following block chain medical data and shares scene: the hospital that medical data is capable of providing in system has 3
Family, needs to have 2 using the scientific research institution of medical data, has 5 block chain users are authorized to become common recognition node in network, i.e.,
Cooperative alliances are shared in medical dataMiddle data owner's quantityData requester quantityCommon recognition node
QuantityMedical data shared procedure carries out on alliance's chain based on practical Byzantine failure tolerance algorithm, the data of generation
By common recognition node verification and it is recorded on block chain.All common recognition nodes do not break down when generating all blocks, and
It is made that consistent response, therefore is normal node.
AllianceIn the medical data type shared have 2 kinds, respectively heart disease data and tuberculosis data, heart disease data
Code name is 1, and tuberculosis data code name is 2, and therefore, the medical data type collection shared in alliance is combined intoScientific research institution
T1And T2It is the data requester in alliance, T1The data of request are heart disease data, T2The data of request be heart disease data and
Tuberculosis data, i.e. R1={ 1 }, R2={ 1,2 };Hospital H1、H2And H3It is the data owner in alliance, is shared in 3 hospitals
Heart disease data have H1And H2, that shares tuberculosis data has H2And H3, i.e. P1={ 1 }, P2={ 1,2 }, P3={ 2 };SPiIt represents
TiIt is the income that alliance obtains, T by providing medical services1Heart disease consulting services, T are provided2Examining for heart disease and tuberculosis is provided
Service is treated, therefore,
The model in above-mentioned Fig. 1 is relied on, when the method for the invention is embodied, takes following steps:
Step A, test set is divided and constructed to the medical data that data owner shares, then calculates F1- index, is had
Body are as follows:
A.1, the data class that step is shared according to all data owners, data owner is gatheredIt is divided into several
A subclass,
When it is implemented,Middle any two intersection of sets collection can be sky, such as h1={ H1,H2, h2=
{H3};
Middle any two intersection of sets collection can not be sky;Such as the present embodiment collects data owner
It closesIt is divided into 2 subclass h1={ H1,H2, h2={ H2,H3};h1And h2Intersection be { H2, non-empty;
A.2, step shares the 2 kinds of medical datas shared in cooperative model according to medical data, constructs 2 test sets, respectively
For heart disease data test collection and tuberculosis data test collection, test set data source is University of California at Irvine machine learning money
Source library (http://archive.ics.uci.edu/ml/index.php);
A.3, the data that step uses data owner to share construct multiple heart disease data training sets and multiple tuberculosis numbers
According to training set, respectively using the corresponding heart disease prediction model of each training set of support vector machines training or tuberculosis prediction model, make
Prediction model is tested with corresponding heart disease data test collection or tuberculosis data test collection, counts TP, TN, FP and FN tetra-
Item prediction result, finally calculates the F1- index of each prediction model;
Specific to the present embodiment, multiple heart disease data training sets of building are respectively as follows: H1Heart disease data set, H2's
Heart disease data set and H1And H2Heart disease data set union;Multiple tuberculosis data training sets of building are respectively as follows: H2
Tuberculosis data set, H3Tuberculosis data acquisition system and H2And H3Tuberculosis data set union.
Using above-mentioned heart disease data training set and tuberculosis data training set, it is respectively trained based on the pre- of support vector machines
Model is surveyed, and calculates the F1- index of prediction model by formula (1), the F1- index of obtained prediction model is as shown in table 1.
1 heart disease of table and tuberculosis prediction model F1- index
Step B, according to the F1- index in formula (5) and table 1, data owner H is calculated1With H2When shared heart disease data
Contributrion margin, be respectively as follows:
And calculate data owner H2With H3Contributrion margin when shared tuberculosis data, is respectively as follows:
Step C, the distribution of income ratio of 5 common recognition nodes is calculated.All common recognition nodes are generating all block Shi Doucheng
For normal node, then the income that each node obtains accounts for the ratio of all common recognition node total revenues are as follows: P1=P2=P3=P4=P5=
1/5。
Step D, medical data is calculated by formula (10), formula (11) and formula (12) and shares cooperative alliancesIn own
The income of member, is respectively as follows:
Embodiment 2
The present embodiment is to compare result of the method for the invention under several scenes, verifies excitation of the invention
Method has incentive action to data owner.Assuming that medical data shares cooperative alliancesIn include 2 data owners, 5
A common recognition node and 1 data requester, i.e.,ChangeIn two data owners
H1And H2Corresponding F1- index withRatio, enable respectivelyIt enables The distribution of income knot of cooperative alliances member is calculated according to step 1 to step 4
Fruit, observation data owner's set.Two data owner H1And H2Respective income accounts for medical data and shares cooperative alliances
Total revenue ratio as shown in table 2 and table 3.
2 data owner H of table1Distribution of income calculated result
3 data owner H of table2Distribution of income calculated result
From table 2 and table 3 as can be seen that for a data ownerWithNumber
The increase of value, data owner HiThe income that can be obtained accounts for medical data and shares cooperative alliancesTotal revenue ratio increase
Add, illustrates that data owner can increase the income of oneself by improving the F1- index of shared data.Therefore, energy of the present invention
Enough excited data owners improve percentage contribution, share more actual medical data.
Embodiment 3
The present embodiment is to compare result of the method for the invention under several scenes, verifies excitation of the invention
Method has incentive action to data requester.Assuming that it includes several data owners that medical data, which shares cooperative alliances, 5 altogether
Know node and 1 data requester, i.e.,Assuming that data owner gathersTotal revenue be expressed asCommon recognition node setTotal revenue be expressed asData requester set
Total revenue be expressed asFor the set of arbitrary data ownerHaveChange
The quantity for becoming data requester, enables the quantity of data ownerIt is counted according to step 1 to step 4
The distribution of income of cooperative alliances member is calculated as a result, observation data owner's total revenueCommon recognition node total revenueAnd number
According to requestor's total revenueIt accounts for medical data and shares cooperative alliancesTotal revenue ratio, as a result as shown in Figure 2.
Figure it is seen that when data owner's quantity increases, data owner's total revenueIt reduces, common recognition node is total
IncomeWith data requester total revenueIncrease, illustrates that data requester can be in the alliance with more data owners
It is middle to obtain more incomes.Therefore, the present invention can excited data requester requests and use more medical datas, on the one hand, number
According to requestor by can be improved the effect of prediction model in medical services provided by it, another party using more medical datas
Face, data requester are shared in medical data by can be improved it with the shared cooperation of more data owners progress medical data
Benefit ratio in cooperative alliances.
The above describes embodiments of the present invention in conjunction with the accompanying drawings and embodiments, but for those skilled in the art
For, under the premise of not departing from this patent principle, additionally it is possible to make several improvement, these are also the protection to belong to this patent
Range.
Claims (3)
1. a kind of block chain medical data based on Charolais cattle shares motivational techniques, it is characterised in that: the medical number relied on
Cooperative alliances are shared including medical data according in shared cooperative modelMedical data and use medical data provide medical treatment clothes
The income of business and generation;
Wherein, medical data shares cooperative alliancesIt is data requester setCommon recognition node setGather with data ownerAnd, i.e., ForThe number of middle data requester,ForThe number of middle common recognition node,ForThe number of middle data owner;
Wherein, the type collection of medical data is combined into Element in set represents medical data type
Code name;The type of medical data isKind, andKind medical data is gathered by data ownerWith data requester set
It is shared;Medical data and medical data share cooperative alliancesRelationship specifically: data owner setIn j-th of data
Owner HjShared data class set expression is Pj, data requester setIn i-th of data requester TiThe number of request
It is R according to type set expressioni, set PjWith set RiIt is setSubset, i.e.,J is more than or equal to 1 and is less than
It is equal toI is more than or equal to 1 and is less than or equal toData owner HjGive the data sharing that type is d to data requester Ti
It indicates are as follows: d ∈ PjAnd d ∈ Ri;D is medical data type setIn an element, i.e.,
Wherein, the income for providing medical services using medical data and generating is usedIt indicates;Meaning be data requester
TiThe income for providing medical services by using type for the data of d and generating;
The block chain medical data shares motivational techniques, includes the following steps:
Step 1 gathers data ownerDivide and constructs test set, training prediction model using medical data, then
F1- index is calculated, specifically:
The data class that step 1.1 is shared according to all data owners, data owner is gatheredIt is divided intoA subset
It closes
Step 1.2 is shared in cooperative model according to medical dataA medical data type, buildingA test set, each
Test set is made of several samples with label,The data class of a test set shares cooperation mould with medical data respectively
In typeKind medical data type is identical;
The medical data building training set and training prediction model of data owner's set h ' shared d type of step 1.3,
Prediction model is tested and statistical forecast as a result, calculate the F1- index of prediction model again;
Wherein, h ' is the set of data owner's composition of shared d type data,
Wherein, hdThe set formed for the data owner of all shared d type data;
Step 1.3 specifically includes following sub-step again:
The data for the d type that step 1.3A is shared using all data owners in data owner's set h ' construct training set;
Step 1.3B utilizes prediction model of the training set data training based on support vector machines;
The test set that step 1.3C is d using the data class constructed in step 1.2, to the prediction mould established in step 1.3B
Type is tested, and obtains the prediction result of all samples in test set, compares the label of prediction result and sample, statistics TP, TN,
The numerical value of tetra- prediction results of FP and FN;
Wherein, TP indicates the quantity of class that the prediction of positive class is positive;TN indicates the quantity of class that the prediction of negative class is negative;FP expression will be born
Class predicts the class that is positive, that is, the quantity reported by mistake, and FN indicates class that the prediction of positive class is negative, that is, the quantity failed to report;
Step 1.3D calculates the F1- index of prediction model by formula (1):
Wherein, F1 (h ') is using the F1- index of the prediction model for the data training shared in h ', and P is the accurate of prediction model
Rate, R are the recall rate of prediction model, are calculated respectively by formula (2) and formula (3):
Step 2 calculates data owner H by formula (4)jContributrion margin in shared d type data
Wherein,For data owner's setRemove HjRemaining all data possess afterwards
The set of person's composition,Meaning be data owner HjData owner is gathered on F1- indexSide
Border contribution, i.e. HjCoalize the difference of front and back F1- change index;
Wherein,For hdAll subsets in include data owner HjSubset composed by set;
Step 3 calculates common recognition node M by formula (5)kIncome account for the ratio P of all common recognition the sum of nodes revenuesk:
Wherein, PkCommon recognition node M is distributed in expressionkIncome account for setIn it is all common recognition node total revenues ratio, n be doctor
Treat the quantity of the block generated in data sharing process, AkFor node M of knowing togetherkAll blocks generated when as normal node
Set composed by serial number, i.e.,qiFor the common recognition section when generating the block of serial number i as normal node
The quantity of point is calculated by formula (6):
Wherein, I is set, i.e. I={ 1 ..., n } composed by the serial number of all blocks;
Step 4 utilizes Shapley value method, the shared cooperative alliances of calculating medical dataIn all members income, pass through formula
(7), formula (8) and formula (9) calculate separately data owner HjIncomeCommon recognition node MkIncomeIt is asked with data
The person of asking TiIncome
Wherein,It is calculated respectively by formula (10), formula (11) and formula (12):
Wherein,For data owner's set hd, common recognition node setWith data requester set { TiAnd, i.e., For setThe quantity of middle data owner, w (x) are the set that allied member's quantity is x
Weighting function, calculated by formula (13):
2. a kind of block chain medical data based on Charolais cattle according to claim 1 shares motivational techniques, feature
Be: medical data shares cooperative alliancesIn all cooperative alliances members in alliance's chain based on practical Byzantine failure tolerance algorithm
It is shared that system carries out medical data;Alliance's chain based on practical Byzantine failure tolerance algorithm is that a kind of cooperative alliances number of members is controllable
And the block chain with high serious forgiveness, it is made of the block of sustainable growth, shared medical data information is by generating block quilt
It is recorded on block chain, all common recognition nodes for reaching an agreement response with final common recognition are normal section during generating block
Point.
3. a kind of block chain medical data based on Charolais cattle according to claim 1 shares motivational techniques, feature
Be: in step 3, k is more than or equal to 1 and is less than or equal to It indicatesThe quantity of middle common recognition node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910379542.7A CN110110008B (en) | 2019-05-08 | 2019-05-08 | Block chain medical data sharing excitation method based on charapril value |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910379542.7A CN110110008B (en) | 2019-05-08 | 2019-05-08 | Block chain medical data sharing excitation method based on charapril value |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110110008A true CN110110008A (en) | 2019-08-09 |
CN110110008B CN110110008B (en) | 2020-12-25 |
Family
ID=67488764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910379542.7A Active CN110110008B (en) | 2019-05-08 | 2019-05-08 | Block chain medical data sharing excitation method based on charapril value |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110008B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110729052A (en) * | 2019-09-10 | 2020-01-24 | 合肥工业大学 | Old health data knowledge analysis method and system |
CN111311257A (en) * | 2020-01-20 | 2020-06-19 | 福州数据技术研究院有限公司 | Medical data sharing excitation method and system based on block chain |
CN111309813A (en) * | 2020-03-17 | 2020-06-19 | 北京百度网讯科技有限公司 | Information processing method, device, equipment and storage medium in data circulation |
CN111324913A (en) * | 2020-02-17 | 2020-06-23 | 咪咕文化科技有限公司 | Collaborative authoring method, platform and computer-readable storage medium based on block chain |
CN111625594A (en) * | 2020-04-22 | 2020-09-04 | 东南大学 | Countless health data bank carrier method based on block chain technology |
CN111639122A (en) * | 2020-04-08 | 2020-09-08 | 广东中科智能区块链技术有限公司 | Alliance chain incentive scheme and device fusing public chains |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103839177A (en) * | 2013-12-26 | 2014-06-04 | 浙江工业大学 | Improved Shapley value method distribution method of micro-grid load gaming |
CN106548291A (en) * | 2016-11-07 | 2017-03-29 | 国网山东省电力公司电力科学研究院 | A kind of micro-capacitance sensor on-road efficiency distribution method based on Shapley values |
CN106600335A (en) * | 2016-12-20 | 2017-04-26 | 广东技术师范学院 | Big data analysis technology-based medical supply chain benefit allocation method |
US20170236196A1 (en) * | 2014-03-31 | 2017-08-17 | Monticello Enterprises, Llc | System and method for transitioning from a first site to a destination site in a one click purchasing state |
CN108805449A (en) * | 2018-06-11 | 2018-11-13 | 南方电网科学研究院有限责任公司 | Cooperative game method towards integrated energy system cost sharing and distribution of income |
-
2019
- 2019-05-08 CN CN201910379542.7A patent/CN110110008B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103839177A (en) * | 2013-12-26 | 2014-06-04 | 浙江工业大学 | Improved Shapley value method distribution method of micro-grid load gaming |
US20170236196A1 (en) * | 2014-03-31 | 2017-08-17 | Monticello Enterprises, Llc | System and method for transitioning from a first site to a destination site in a one click purchasing state |
CN106548291A (en) * | 2016-11-07 | 2017-03-29 | 国网山东省电力公司电力科学研究院 | A kind of micro-capacitance sensor on-road efficiency distribution method based on Shapley values |
CN106600335A (en) * | 2016-12-20 | 2017-04-26 | 广东技术师范学院 | Big data analysis technology-based medical supply chain benefit allocation method |
CN108805449A (en) * | 2018-06-11 | 2018-11-13 | 南方电网科学研究院有限责任公司 | Cooperative game method towards integrated energy system cost sharing and distribution of income |
Non-Patent Citations (2)
Title |
---|
刘怡然: ""基于沙普利值计算的区块链中PoS共识机制的改进"", 《计算机研究与发展》 * |
祝烈煌: ""区块链隐私保护研究综述"", 《计算机研究与发展》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110729052A (en) * | 2019-09-10 | 2020-01-24 | 合肥工业大学 | Old health data knowledge analysis method and system |
CN111311257A (en) * | 2020-01-20 | 2020-06-19 | 福州数据技术研究院有限公司 | Medical data sharing excitation method and system based on block chain |
CN111324913A (en) * | 2020-02-17 | 2020-06-23 | 咪咕文化科技有限公司 | Collaborative authoring method, platform and computer-readable storage medium based on block chain |
CN111309813A (en) * | 2020-03-17 | 2020-06-19 | 北京百度网讯科技有限公司 | Information processing method, device, equipment and storage medium in data circulation |
CN111309813B (en) * | 2020-03-17 | 2023-08-29 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for processing information in data circulation |
CN111639122A (en) * | 2020-04-08 | 2020-09-08 | 广东中科智能区块链技术有限公司 | Alliance chain incentive scheme and device fusing public chains |
CN111639122B (en) * | 2020-04-08 | 2023-04-18 | 广东中科智能区块链技术有限公司 | Public chain fused alliance chain excitation scheme and device |
CN111625594A (en) * | 2020-04-22 | 2020-09-04 | 东南大学 | Countless health data bank carrier method based on block chain technology |
Also Published As
Publication number | Publication date |
---|---|
CN110110008B (en) | 2020-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110110008A (en) | A kind of shared motivational techniques of the block chain medical data based on Charolais cattle | |
CN109636061A (en) | Training method, device, equipment and the storage medium of medical insurance Fraud Prediction network | |
Mielczarek | Review of modelling approaches for healthcare simulation | |
Grieco et al. | Performance assessment using mixed effects models: a case study on coronary patient care | |
Liu et al. | The application of the machine learning method in electromyographic data | |
Zhang et al. | Continuous-Time decision transformer for healthcare applications | |
Chen et al. | A multi-feature and time-aware-based stress evaluation mechanism for mental status adjustment | |
Oguntimilehin et al. | A machine learning based clinical decision support system for diagnosis and treatment of typhoid fever | |
Bezjak et al. | A preliminary survey of oncologists' perceptions of quality of life information | |
Rosser | The history of health related quality of life in 10 1/2 paragraphs | |
Liu et al. | CR-GAT: Consistency regularization enhanced graph attention network for semi-supervised EEG emotion recognition | |
Na et al. | Humans use forward thinking to exert social control | |
Zhen et al. | To learn or to gain: neural signatures of exploration in human decision-making | |
CN112329921B (en) | Diuretic dose reasoning equipment based on deep characterization learning and reinforcement learning | |
Pecoraro et al. | Agent Based Modelling for Simulating the Interregional Patient Mobility in Italy | |
Hong et al. | Inquiring diagnosis system of traditional Chinese medicine | |
Gupta et al. | Human decision making modelling for gambling task under uncertainty and risk | |
Wilson et al. | Brain activity in the play of dominant strategy and mixed strategy games | |
CN110634541A (en) | Oral health data acquisition and analysis method | |
Shen et al. | A quantitative quality control method of big data in cancer patients using artificial neural network | |
Ngo et al. | Federated Fuzzy Clustering for Decentralized Incomplete Longitudinal Behavioral Data | |
Moradi et al. | MetaSyCar: a system for metabolic syndrome control and caring | |
Li et al. | Study on Health Behavior Pattern of Community Residents in Public Health Emergency | |
Huarng et al. | Artificial Intelligence in Healthcare | |
Mwaniki | The Role of Artificial Intelligence in Diagnostic Radiology: Knowledge, Attitude, and Practice of Radiologists and Radiology Residents in Kenya |
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 |