CN109411093A - A kind of intelligent medical treatment big data analysis processing method based on cloud computing - Google Patents
A kind of intelligent medical treatment big data analysis processing method based on cloud computing Download PDFInfo
- Publication number
- CN109411093A CN109411093A CN201811203541.9A CN201811203541A CN109411093A CN 109411093 A CN109411093 A CN 109411093A CN 201811203541 A CN201811203541 A CN 201811203541A CN 109411093 A CN109411093 A CN 109411093A
- Authority
- CN
- China
- Prior art keywords
- data
- medical treatment
- intelligent medical
- task
- time
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 8
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000003044 adaptive effect Effects 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000005065 mining Methods 0.000 claims abstract description 7
- 230000001225 therapeutic effect Effects 0.000 claims abstract description 7
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 4
- 239000002245 particle Substances 0.000 claims description 19
- 238000003745 diagnosis Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000005312 nonlinear dynamic Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims 1
- 238000007418 data mining Methods 0.000 abstract description 6
- 238000013467 fragmentation Methods 0.000 abstract description 4
- 238000006062 fragmentation reaction Methods 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The intelligent medical treatment big data analysis processing method based on cloud computing that the invention discloses a kind of.It specifically includes that and merges the data in all intelligent medical treatment databases, data are pre-processed, convenient for obtaining the mining effect of high quality；The association in intelligent medical treatment big data between project set is excavated by Cyclic Association Rules, is conducive to collect the detailed case history of user, provides basis to formulate accurately and effectively therapeutic scheme；Task schedule is carried out to bid associated data library by adaptive weighting population, the quality of inquiry velocity and query result is improved, completes the query optimization of intelligent medical treatment big data.This method has preferable data cover and real-time, and medical information is integrated and forms the intelligent medical treatment big data quick reference system that can be found with depth, the data information of quick search distributing fragmentation while realizing data mining process.
Description
Technical field
The invention belongs to intelligent medical treatment, data mining, particles to optimize field, and in particular to a kind of wisdom based on cloud computing
Medical big data analysis processing method.
Background technique
Intelligent medical treatment is different from traditional medical, and intelligent medical treatment, not only will be using people in different location based on data
Medical treatment, health, physical examination information, it is also necessary to excavate and processing people's clothing, food, lodging and transportion -- basic necessities of life every aspect medical treatment & health data, and this
Not only geographical location disperses a little data, and place platform also extremely disperses, therefore existing querying method is facing distributing fragment
When realizing that data effectively excavate this application scenarios while changing inquiry, often there are query timeout even feelings of the system without response
Condition.
Summary of the invention
To solve the above problems, integrate medical information and form one can be deep the purpose of the present invention is to provide a kind of
The intelligent medical treatment big data quick reference system of discovery is spent, quick search distributing fragmentation while realizing data mining process
Data information.
The present invention solves the problems, such as technical solution used by it, comprising the following steps:
A kind of intelligent medical treatment big data analysis processing method based on cloud computing, includes the following steps:
A. the data in all intelligent medical treatment databases are merged, data is pre-processed, it is high-quality convenient for obtaining
The mining effect of amount；
B. the association in intelligent medical treatment big data between project set is excavated by Cyclic Association Rules, is conducive to collect
The detailed case history of user provides basis to formulate accurately and effectively therapeutic scheme；
C. task schedule is carried out to bid associated data library by adaptive weighting population, improves inquiry velocity and inquiry
As a result quality completes the query optimization of intelligent medical treatment big data.
Further, the specific implementation of the step A are as follows:
(1) to the data x of the variable space in intelligent medical treatment databaseiIt is reconfigured, extracts the comprehensive of database and become
Database object, is considered as the set of variable by amount, then generalized variable is the linear combination of variable:
Wherein, μkiIt is the combination coefficient of generalized variable, k is the quantity of generalized variable；
(2) the tables of data X with n variable, the variance of generalized variable are converted by database are as follows:
Wherein,It is the covariance matrix of variable, constructs Lagrange's equation:
L=μTCμ-λμTμ+λ
Wherein, λ is Lagrange coefficient, seeks the local derviation of equation:
Enabling local derviation is 0, then has μTμ=1, C μ=λ μ, therefore
V (f)=μTC μ=μTλ μ=λ
Therefore μ is the standardized feature variable of Matrix C, and the Lagrange's equation of k generalized variable is all solved and is finished,
The generalized variable database of the standardized feature variable composition of extraction does not have redundancy, and database is enable to cover original as much as possible
Variation information in database, and dimension-reduction treatment is carried out to high dimensional variable space, to obtain the mining effect of high quality.
Further, the specific implementation of the step B are as follows:
(1) medical data of each user forms a set A=a in the database D obtained after pre-processing1,a2,…,
am, for element X, Y the ∈ D in database, andIf ratio shared by X ∪ Y is s in database, X, Y have
The support of correlation rule is s, if it also includes Y that the set in database comprising X, which has the set that accounting is c, X, Y, which have, to be associated with
The confidence level of rule is c, if the support and confidence level of X, Y are greater than the minimum support and Minimum support4 of setting, then X, Y are closed
Connection rule is set up；
(2) time of origin for setting up each Medical treatment of every user is T, whens diagnosis and treatment a length of l, total duration L judges to close
Whether connection rule has periodicity c: setting up classification number k, the time in first diagnosis and treatment period is divided into k according to clustering
Section:
The k class medical data of user is xi+1,xi+2,…,xj, each there is m dimension, mean vector are as follows:
Then class indicates are as follows:
Establish objective function:
(2) minimum classification of objective function are as follows:
Calculate minimal point ik, obtain kth class { ik+1,ik+2,…,in, it successively calculates, obtains all classes, be optimal solution,
By the frequency that diagnosis and treatment occur, the period is determined using clustering, and periodically frequently set x is obtained by optimization, it is more a certain
Whether x meets minimum support in period, if satisfied, then retaining, otherwise deletes, so that correlation rule is obtained, it is accurate to formulate
Effective therapeutic scheme provides basis.
Further, the specific implementation of the step C are as follows:
(1) it will be excavated by correlation rule and the data collected of classifying form intelligent medical treatment large database concept, established
Information query task under cloud computing environment, medical data query task is as a task schedule node, Mei Geren each time
Scheduling strategy be engaged in as a particle, intelligent medical treatment big data query task is divided into multiple queries according to each hospital and is appointed
Business is divided into three-level inquiry subtask further according to inquiry content, by earliest possible time started time of task nodeiAs node
Weight traverses the time of all nodesi, earliest idle node will be called preferentially, in scheduling process, the time of nodeiIt will
Constantly variation, foundation are generated Q scheduling strategy, { x by system at randomi1,xi2,…,xinRepresent the position of particle, i.e. task point
It is fitted on processor and executes, { vi1,vi2,…,vinThe speed that represents particle, the position of subsequent time particle is obtained by speed；
(2) task is completed into total time as objective function:
Wherein, T (i, j) be j-th of subtask be assigned to run on i-th of processor required for the time, m is herein
The quantity of subtask on reason machine, cost needed for task schedule is as auxiliary function:
Wherein, c (i, j) is that j-th of subtask is assigned to cost required for operation on i-th of processor, and n is processor
Quantity fitness function is obtained according to the weight of two functions:
F=ω1Ti+ω2Ci
Wherein, ω1、ω2It is the weight of the function of time and cost function, therefore, each particle has an adaptive value；
(3) when there is task to need to dispatch, a processor p is randomly selectediProcessing task node nj, determine njIn piOn
The earliest time time that can startij, one processor p of every selectioniTo place task node njWhen, just calculate task at this time
Adaptive value, pass through Nonlinear Dynamic weight update adaptive value:
Wherein, N is the number of iterations, and particle chooses the position that can obtain bigger adaptive value as best after each iteration
, so as to most obtain query result fastly, wisdom is completed until meeting the number of iterations of setting in the best position in position and group
The query optimization of medical big data.
The beneficial effects of the present invention are:
With preferable data cover and real-time, medical information is integrated and forms the intelligence that can be found with depth
Intelligent medical treatment big data quick reference system, the data letter of quick search distributing fragmentation while realizing data mining process
Breath.
Detailed description of the invention
Fig. 1 is a kind of overall flow figure of intelligent medical treatment big data analysis processing method based on cloud computing；
Fig. 2 is intelligent medical treatment data mining structure chart；
Fig. 3 is intelligent medical treatment big data query optimization flow chart.
Specific embodiment
Referring to Fig.1, method of the present invention the following steps are included:
A. the data in all intelligent medical treatment databases are merged, data is pre-processed, it is high-quality convenient for obtaining
The mining effect of amount；
(1) data in all intelligent medical treatment databases being merged, database includes the information of many complex redundancies,
It is difficult to ensure the consistency of database.To the data x of the variable space in databaseiIt is reconfigured, extracts the comprehensive of database
Variable is closed, to utmostly cover the Global Information of database.Database object is considered as to the set of variable, then generalized variable
For the linear combination of variable:
Wherein, μkiIt is the combination coefficient of generalized variable, k is the quantity of generalized variable.
(2) the tables of data X with n variable, the variance of generalized variable are converted by database are as follows:
Wherein,It is the covariance matrix of variable, constructs Lagrange's equation:
L=μTCμ-λμTμ+λ
Wherein, λ is Lagrange coefficient.Seek the local derviation of equation:
Enabling local derviation is 0, then has μTμ=1, C μ=λ μ.Therefore
V (f)=μTC μ=μTλ μ=λ
Therefore μ is the standardized feature variable of Matrix C.The Lagrange's equation of k generalized variable is all solved and is finished,
The generalized variable database of the standardized feature variable composition of extraction does not have redundancy, and database is enable to cover original as much as possible
Variation information in database, and dimension-reduction treatment is carried out to high dimensional variable space, convenient for obtaining the mining effect of high quality.
B. the association in intelligent medical treatment big data between project set is excavated by Cyclic Association Rules, is conducive to collect
The detailed case history of user provides basic (such as Fig. 2) to formulate accurately and effectively therapeutic scheme；
(1) medical data of each user forms a set A=a in the database D obtained after pre-processing1,a2,…,
am, for element X, Y the ∈ D in database, andIf ratio shared by X ∪ Y is s in database, X, Y have
The support of correlation rule is s, if it also includes Y that the set in database comprising X, which has the set that accounting is c, X, Y, which have, to be associated with
The confidence level of rule is c.If the support and confidence level of X, Y are greater than the minimum support and Minimum support4 of setting, then X, Y is closed
Connection rule is set up.
(2) time of origin for setting up each Medical treatment of every user is T, whens diagnosis and treatment a length of l, total duration L.Judgement is closed
Whether connection rule has periodicity c: setting up classification number k, the time in first diagnosis and treatment period is divided into k according to clustering
Section:
The k class medical data of user is xi+1,xi+2,…,xj, each there is m dimension, mean vector are as follows:
Then class indicates are as follows:
Establish objective function:
(2) minimum classification of objective function are as follows:
Calculate minimal point ik, obtain kth class { ik+1,ik+2,…,in, it successively calculates, obtains all classes, be optimal solution.
By the frequency that diagnosis and treatment occur, the period is determined using clustering, and periodically frequently set x is obtained by optimization, it is more a certain
Whether x meets minimum support in period, if satisfied, then retaining, otherwise deletes, so that correlation rule is obtained, it is accurate to formulate
Effective therapeutic scheme provides basis.
C. task schedule is carried out to bid associated data library by adaptive weighting population, improves inquiry velocity and inquiry
As a result quality completes the query optimization (such as Fig. 3) of intelligent medical treatment big data.
(1) it will be excavated by correlation rule and the data collected of classifying form intelligent medical treatment large database concept, established
Information query task under cloud computing environment, medical data query task is as a task schedule node, Mei Geren each time
Scheduling strategy be engaged in as a particle.Intelligent medical treatment big data query task is divided into multiple queries according to each hospital to appoint
Business is divided into three-level inquiry subtask further according to inquiry content.By earliest possible time started time of task nodeiAs node
Weight traverses the time of all nodesi, earliest idle node will be called preferentially, in scheduling process, the time of nodeiIt will
Constantly variation.Foundation is generated Q scheduling strategy, { x by system at randomi1,xi2,…,xinRepresent the position of particle, i.e. task point
It is fitted on processor and executes.{vi1,vi2,…,vinThe speed that represents particle, the position of subsequent time particle is obtained by speed.
(2) task is completed into total time as objective function:
Wherein, T (i, j) is that j-th of subtask is assigned to the time required for operation on i-th of processor, and m is this processing
The quantity of subtask on machine.Cost needed for task schedule is as auxiliary function:
Wherein, c (i, j) is that j-th of subtask is assigned to cost required for operation on i-th of processor, and n is processor
Quantity.According to the weight of two functions, fitness function is obtained:
F=ω1Ti+ω2Ci
Wherein, ω1、ω2It is the weight of the function of time and cost function.Therefore, each particle has an adaptive value.
(3) when there is task to need to dispatch, a processor p is randomly selectediProcessing task node nj, determine njIn piOn
The earliest time time that can startij, one processor p of every selectioniTo place task node njWhen, just calculate task at this time
Adaptive value.Adaptive value is updated by Nonlinear Dynamic weight:
Wherein, N is the number of iterations.Particle chooses the position that can obtain bigger adaptive value as best after each iteration
, so as to most obtain query result fastly, wisdom is completed until meeting the number of iterations of setting in the best position in position and group
The query optimization of medical big data.
In conclusion just completing a kind of intelligent medical treatment big data analysis processing side based on cloud computing of the present invention
Method.This method has preferable data cover and real-time, and medical information is integrated and forms one can be with depth discovery
Intelligent medical treatment big data quick reference system, the data letter of quick search distributing fragmentation while realizing data mining process
Breath.
Claims (4)
1. a kind of intelligent medical treatment big data analysis processing method based on cloud computing, which comprises the steps of:
A. the data in all intelligent medical treatment databases are merged, data is pre-processed, convenient for obtaining high quality
Mining effect；
B. the association in intelligent medical treatment big data between project set is excavated by Cyclic Association Rules, is conducive to collect user
Detailed case history provides basis to formulate accurately and effectively therapeutic scheme；
C. task schedule is carried out to bid associated data library by adaptive weighting population, improves inquiry velocity and query result
Quality, complete intelligent medical treatment big data query optimization.
2. the intelligent medical treatment big data enquiring and optimizing method based on cloud computing as described in claim 1, which is characterized in that described
The specific implementation of step A are as follows:
(1) to the data x of the variable space in intelligent medical treatment databaseiIt is reconfigured, extracts the generalized variable of database, it will
Database object is considered as the set of variable, then generalized variable is the linear combination of variable:
Wherein, μkiIt is the combination coefficient of generalized variable, k is the quantity of generalized variable；
(2) the tables of data X with n variable, the variance of generalized variable are converted by database are as follows:
Wherein,It is the covariance matrix of variable, constructs Lagrange's equation:
L=μTCμ-λμTμ+λ
Wherein, λ is Lagrange coefficient, seeks the local derviation of equation:
Enabling local derviation is 0, then has μTμ=1, C μ=λ μ, therefore
V (f)=μTC μ=μTλ μ=λ
Therefore μ is the standardized feature variable of Matrix C, and the Lagrange's equation of k generalized variable is all solved and is finished, and is extracted
The generalized variable database of standardized feature variable composition there is no redundancy, so that database is covered former data as much as possible
Variation information in library, and dimension-reduction treatment is carried out to high dimensional variable space, to obtain the mining effect of high quality.
3. the intelligent medical treatment big data enquiring and optimizing method based on cloud computing as claimed in claim 2, which is characterized in that described
The specific implementation of step B are as follows:
(1) medical data of each user forms a set A=a in the database D obtained after pre-processing1, a2..., am, right
Element X, Y ∈ D in database, andIf ratio shared by X ∪ Y is s in database, X, Y have association rule
Support then is s, if it also includes Y that the set in database comprising X, which has the set that accounting is c, X, Y are with correlation rule
Confidence level is c, if the support and confidence level of X, Y are greater than the minimum support and Minimum support4 of setting, then X, Y correlation rule
It sets up；
(2) time of origin for setting up each Medical treatment of every user is T, whens diagnosis and treatment a length of I, total duration L, judge association rule
Then whether there is periodicity c: setting up classification number k, the time in first diagnosis and treatment period is divided into k sections according to clustering:
The k class medical data of user is xi+1, xi+2..., xj, each there is m dimension, mean vector are as follows:
Then class indicates are as follows:
Establish objective function:
(2) minimum classification of objective function are as follows:
Calculate minimal point ik, obtain kth class { ik+1, ik+2..., in, it successively calculates, obtains all classes, be optimal solution, feeling
The frequency for controlling generation determines the period using clustering, obtains periodically frequently set X, more a certain period by optimization
Whether middle X meets minimum support, if satisfied, then retaining, otherwise deletes, so that correlation rule is obtained, to formulate accurate and effective
Therapeutic scheme provide basis.
4. the intelligent medical treatment big data enquiring and optimizing method based on cloud computing as claimed in claim 3, which is characterized in that described
The specific implementation of step C are as follows:
(1) it will be excavated by correlation rule and the data collected of classifying form intelligent medical treatment large database concept, establish cloud meter
The information query task under environment is calculated, medical data query task is as a task schedule node, each task tune each time
Degree strategy is used as a particle, and intelligent medical treatment big data query task is divided into multiple queries subtask according to each hospital, then
It is divided into three-level inquiry subtask according to inquiry content, by earliest possible time started time of task nodeiAs node weight,
Traverse the time of all nodesi, earliest idle node will be called preferentially, in scheduling process, the time of nodeiIt will be continuous
Variation, foundation are generated Q scheduling strategy, { x by system at randomi1, xi2..., xinRepresenting the position of particle, i.e. task is assigned to
It is executed on processor, { vi1, vi2..., vinThe speed that represents particle, the position of subsequent time particle is obtained by speed；
(2) task is completed into total time as objective function:
Wherein, T (i, j) is that j-th of subtask is assigned to the time required for operation on i-th of processor, and m is on this processor
The quantity of subtask, cost needed for task schedule is as auxiliary function:
Wherein, c (i, j) is that j-th of subtask is assigned to cost required for operation on i-th of processor, and n is the number of processor
Amount, according to the weight of two functions, obtains fitness function:
F=ω1Ti+ω2Ci
Wherein, ω1、ω2It is the weight of the function of time and cost function, therefore, each particle has an adaptive value；
(3) when there is task to need to dispatch, a processor p is randomly selectediProcessing task node nj, determine njIn piOn can
The earliest time time of beginningij, one processor p of every selectioniTo place task node njWhen, just calculate the adaptation of task at this time
Value updates adaptive value by Nonlinear Dynamic weight:
Wherein, N is the number of iterations, and particle chooses the position that can obtain bigger adaptive value as best position after each iteration
, so as to most obtain query result fastly, intelligent medical treatment is completed until meeting the number of iterations of setting in the best position with group
The query optimization of big data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811203541.9A CN109411093B (en) | 2018-10-16 | 2018-10-16 | Intelligent medical big data analysis processing method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811203541.9A CN109411093B (en) | 2018-10-16 | 2018-10-16 | Intelligent medical big data analysis processing method based on cloud computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109411093A true CN109411093A (en) | 2019-03-01 |
| CN109411093B CN109411093B (en) | 2022-03-18 |
Family
ID=65468174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811203541.9A Active CN109411093B (en) | 2018-10-16 | 2018-10-16 | Intelligent medical big data analysis processing method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109411093B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674230A (en) * | 2019-09-25 | 2020-01-10 | 重庆邮电大学 | Intelligent edge data classification storage method |
| CN111091897A (en) * | 2019-10-16 | 2020-05-01 | 上海得辛医疗科技服务有限公司 | Medical institution supplier cooperation method based on Internet technology |
| CN111126717A (en) * | 2020-02-05 | 2020-05-08 | 江苏星月测绘科技股份有限公司 | Space-time big data sharing and service model construction method |
| CN111161879A (en) * | 2020-02-24 | 2020-05-15 | 梅里医疗科技(洋浦)有限责任公司 | Disease prediction system based on big data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202883A (en) * | 2016-06-28 | 2016-12-07 | 成都中医药大学 | A kind of method setting up disease cloud atlas based on big data analysis |
| US20170091642A1 (en) * | 2015-09-24 | 2017-03-30 | Sas Institute Inc. | Techniques to provide real-time processing enhancements and modeling for data anomaly detection pertaining to medical events using decision trees |
| CN106911813A (en) * | 2017-05-08 | 2017-06-30 | 上海喆之信息科技有限公司 | A kind of Mobile medical system of the use mobile terminal based on cloud |
| CN107330238A (en) * | 2016-08-12 | 2017-11-07 | 中国科学院上海技术物理研究所 | Medical information collection, processing, storage and display methods and device |
| CN107358035A (en) * | 2017-06-28 | 2017-11-17 | 广东技术师范学院 | A kind of portable medical data digging system |
| CN107578797A (en) * | 2016-07-04 | 2018-01-12 | 胡峰 | The method and its system that a kind of health diagnosis and treatment scheme based on cloud computing is recommended |
| CN107767948A (en) * | 2017-10-30 | 2018-03-06 | 深圳市宏数科技有限公司 | It is classified diagnosis and treatment cloud platform |
| CN107808692A (en) * | 2016-09-08 | 2018-03-16 | 上海交迅智能科技有限公司 | Digital medical system and method |
| CN108172299A (en) * | 2017-12-25 | 2018-06-15 | 华中科技大学同济医学院附属协和医院 | A kind of medical data distal end computing system and method |
| CN108573758A (en) * | 2018-04-26 | 2018-09-25 | 贵州大学 | A kind of intelligent medical big data service system and application process |
-
2018
- 2018-10-16 CN CN201811203541.9A patent/CN109411093B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170091642A1 (en) * | 2015-09-24 | 2017-03-30 | Sas Institute Inc. | Techniques to provide real-time processing enhancements and modeling for data anomaly detection pertaining to medical events using decision trees |
| CN106202883A (en) * | 2016-06-28 | 2016-12-07 | 成都中医药大学 | A kind of method setting up disease cloud atlas based on big data analysis |
| CN107578797A (en) * | 2016-07-04 | 2018-01-12 | 胡峰 | The method and its system that a kind of health diagnosis and treatment scheme based on cloud computing is recommended |
| CN107330238A (en) * | 2016-08-12 | 2017-11-07 | 中国科学院上海技术物理研究所 | Medical information collection, processing, storage and display methods and device |
| CN107808692A (en) * | 2016-09-08 | 2018-03-16 | 上海交迅智能科技有限公司 | Digital medical system and method |
| CN106911813A (en) * | 2017-05-08 | 2017-06-30 | 上海喆之信息科技有限公司 | A kind of Mobile medical system of the use mobile terminal based on cloud |
| CN107358035A (en) * | 2017-06-28 | 2017-11-17 | 广东技术师范学院 | A kind of portable medical data digging system |
| CN107767948A (en) * | 2017-10-30 | 2018-03-06 | 深圳市宏数科技有限公司 | It is classified diagnosis and treatment cloud platform |
| CN108172299A (en) * | 2017-12-25 | 2018-06-15 | 华中科技大学同济医学院附属协和医院 | A kind of medical data distal end computing system and method |
| CN108573758A (en) * | 2018-04-26 | 2018-09-25 | 贵州大学 | A kind of intelligent medical big data service system and application process |
Non-Patent Citations (2)
| Title |
|---|
| 王雪等: "基于Apriori算法的数据挖掘在移动医疗终端系统中的研究", 《数字技术与应用》 * |
| 蹇旭: "基于改进粒子群的云计算任务调度方法", 《海南热带海洋学院学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674230A (en) * | 2019-09-25 | 2020-01-10 | 重庆邮电大学 | Intelligent edge data classification storage method |
| CN110674230B (en) * | 2019-09-25 | 2022-10-14 | 重庆邮电大学 | Intelligent edge data classification storage method |
| CN111091897A (en) * | 2019-10-16 | 2020-05-01 | 上海得辛医疗科技服务有限公司 | Medical institution supplier cooperation method based on Internet technology |
| CN111126717A (en) * | 2020-02-05 | 2020-05-08 | 江苏星月测绘科技股份有限公司 | Space-time big data sharing and service model construction method |
| CN111126717B (en) * | 2020-02-05 | 2020-11-06 | 江苏星月测绘科技股份有限公司 | Space-time big data sharing and service model construction method |
| CN111161879A (en) * | 2020-02-24 | 2020-05-15 | 梅里医疗科技(洋浦)有限责任公司 | Disease prediction system based on big data |
| CN111161879B (en) * | 2020-02-24 | 2020-10-09 | 吾征智能技术(北京)有限公司 | Disease prediction system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109411093B (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107193967A (en) | A kind of multi-source heterogeneous industry field big data handles full link solution | |
| CN109411093A (en) | A kind of intelligent medical treatment big data analysis processing method based on cloud computing | |
| CN108399748B (en) | Road travel time prediction method based on random forest and clustering algorithm | |
| Du et al. | Managing noncooperative behaviors in large-scale group decision-making: Integration of independent and supervised consensus-reaching models | |
| Khatibi Bardsiri et al. | A PSO-based model to increase the accuracy of software development effort estimation | |
| CN108874959B (en) | User dynamic interest model building method based on big data technology | |
| Sylejmani et al. | Planning the trip itinerary for tourist groups | |
| CN110008259A (en) | The method and terminal device of visualized data analysis | |
| Rahman et al. | Discretization of continuous attributes through low frequency numerical values and attribute interdependency | |
| CN105260171B (en) | A kind of generation method and device of virtual item | |
| KR101732319B1 (en) | IRIS: Goal-oriented big data business analytics framework | |
| CN105205052B (en) | A kind of data digging method and device | |
| CN104699786A (en) | Semantic intelligent search communication network complaint system | |
| CN111222847B (en) | Open source community developer recommendation method based on deep learning and unsupervised clustering | |
| CN107038263A (en) | A kind of chess game optimization method based on data collection of illustrative plates, Information Atlas and knowledge mapping towards Transac-tion processing efficiency | |
| Yang et al. | Ant colony classification mining algorithm based on pheromone attraction and exclusion | |
| CN110737805A (en) | Method and device for processing graph model data and terminal equipment | |
| Krishnamoorthi et al. | ABK-means: an algorithm for data clustering using ABC and K-means algorithm | |
| Cao et al. | Points-of-interest recommendation algorithm based on LBSN in edge computing environment | |
| CN109684561A (en) | Based on user register Behavioral change Deep Semantics analysis point of interest recommended method | |
| CN109977979A (en) | Position method, apparatus, electronic equipment and the storage medium of seed user | |
| CN114048396B (en) | NQI service recommendation method and system based on heterogeneous information network and deep learning | |
| Pal | Artificial immune‐based supervised classifier for land‐cover classification | |
| Thakkar et al. | Rule based and association rule mining on agriculture dataset | |
| Karanika et al. | Optimized analytics query allocation at the edge of the network |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220209 Address after: Room 213, Yijing building, No.1 Hengshan Road, Yantai Economic and Technological Development Zone, Shandong Province Applicant after: Shandong Yanhuang Industrial Design Co.,Ltd. Address before: 264006 room 505, 5th floor, Jindong business building, Yantai Economic and Technological Development Zone, Shandong Province Applicant before: YANTAI HANNING INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20220225 Address after: 100000 room 206-1, floor 2, building 201, yard 10, Jiuxianqiao North Road, Chaoyang District, Beijing Applicant after: Guokang Zhongjian (Beijing) Health Technology Co.,Ltd. Address before: Room 213, Yijing building, No.1 Hengshan Road, Yantai Economic and Technological Development Zone, Shandong Province Applicant before: Shandong Yanhuang Industrial Design Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100000 room 206-1, floor 2, building 201, yard 10, Jiuxianqiao North Road, Chaoyang District, Beijing Patentee after: Guokang Zhongjian (Beijing) Technology Co.,Ltd. Address before: 100000 room 206-1, floor 2, building 201, yard 10, Jiuxianqiao North Road, Chaoyang District, Beijing Patentee before: Guokang Zhongjian (Beijing) Health Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231107 Address after: 6715, 6th floor, No. 5 Guangyuanzha, Zizhuyuan Road, Haidian District, Beijing, 100080 Patentee after: Beijing Future Cloud Technology Co.,Ltd. Address before: 100000 room 206-1, floor 2, building 201, yard 10, Jiuxianqiao North Road, Chaoyang District, Beijing Patentee before: Guokang Zhongjian (Beijing) Technology Co.,Ltd. |