CN108197737A - A kind of method and system for establishing medical insurance hospitalization cost prediction model - Google Patents
A kind of method and system for establishing medical insurance hospitalization cost prediction model Download PDFInfo
- Publication number
- CN108197737A CN108197737A CN201711471828.5A CN201711471828A CN108197737A CN 108197737 A CN108197737 A CN 108197737A CN 201711471828 A CN201711471828 A CN 201711471828A CN 108197737 A CN108197737 A CN 108197737A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- training
- prediction
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of method and system for establishing medical insurance hospitalization cost prediction model, by prediction model Continuous optimization process, the incremental data of taken at regular intervals social security data, and preserve into tranining database；According to the forecast result of model of the previous version prediction model of incremental data verification, obtained model prediction result is compared with actual value, retriggered and Boot Model training mission are determined whether according to reduced value gap size, sample data after training updates is optimized by machine learning algorithm, to build better prediction model and storage.Based on data are endlessly increased newly, prediction effect is tracked, Continuous optimization realizes optimal model construction system.
Description
Technical field
The present invention relates to big data processing technology fields, and in particular to a kind of side for establishing medical insurance hospitalization cost prediction model
Method and system.
Background technology
In recent years, various disease incidents are climbed to a higher point always, and thing followed medical treatment expense becomes one big heavy burden of people,
It has been a great concern, when especially the patient's condition is seriously needed in hospital, expensive medical treatment expense there may come a time when to become active treatment
Large drag forces.If patient can assume charge to anaphase cost, needed for oneself in advance, the allowable expense of medical insurance etc. has
One understanding, on the one hand can compare multiple hospitals and make optimal selection, on the other hand can know very well in one's heart, carry out fund in advance
Prepare.Usually in life, people often make an anticipation according to historical experience, find, disease phase similar to oneself situation
Same, agematched case is used as with reference to being estimated, it is not difficult to find that historical data is exactly to predict the important evidence in future.
Under the background of medical insurance medical information fast development, medical insurance settlement data also in rapid growth, has had accumulated at present
Fairly large data resource, at the same time, the information technologies such as big data, artificial intelligence, internet are fast-developing, precious number
According to resource and advanced technology to realize that medical insurance hospitalization cost predicts that this current demand provides double shield.
However country's medical insurance work development is later, rarely has at present for the research in terms of medical insurance hospitalization cost prediction model,
Fail to efficiently use social security data, fail to form modeling data by analytical integration and fail rapid build to predict
Model and Continuous optimization.A kind of existing medical treatment big data analysis method, as China Patent No. CN105117587A discloses medical insurance
Intelligent analysis method based on medical big data in field, by hospital's original medical data pick-up and cleaning, then curing again
Different Data Marts is established under the frame of institute's medical profession, to carry out fine granularity analysis to the data of hospital, and being capable of each family
The difference of hospital makes corresponding adjustment, to meet the different demands of each hospital, then by each Data Mart sets up data
Warehouse finally carries out the inquiry of data, and by data visualization using multidimensional analysis language.The intelligence of i.e. above-mentioned medical data point
Analysis method is statistical data analysis, is mainly used for carrying out fine-grained classification and division to hospital's medical insurance business datum.Static number
Analysis method according to statistics can not be applicable in and merge the medical medical insurance big data of continuous renewal, can not fully excavate medical insurance big data
Present in rule, cause analysis model not perfect, analysis result is inaccurate.
Invention content
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of method for establishing medical insurance hospitalization cost prediction model and it is
It unites, Continuous optimization is carried out to prediction model by newly-increased data, with raising to medical insurance hospitalization cost forecasting reliability and accurately
Property.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs：It is a kind of that establish medical insurance hospitalization cost pre-
The method for surveying model, including prediction model initial construction process and prediction model Continuous optimization process, the prediction model continues
Optimization process includes：
Acquire incremental data：The incremental data of taken at regular intervals social security data, and preserve into tranining database；
Optimize training pattern：According to the forecast result of model of the pre- previous version prediction model of incremental data verification, by what is obtained
Model prediction result is compared with actual value, determines whether retriggered according to reduced value gap size and Boot Model is trained
Task optimizes sample data after training updates, to build better prediction model and storage by machine learning algorithm.
Preferably, the prediction model initial construction process includes：
Acquire primary data：The primary data of social security data is extracted, forms initial training sample, and preserve to training data
In library；
Training pattern：It is defined according to model training, transfers initial training sample in tranining database, be started and carried out model
Training mission trains initial sample to build prediction model for the first time and store by machine learning algorithm.
Present invention simultaneously discloses a kind of system for establishing medical insurance hospitalization cost prediction model, the system comprises：
Data acquisition module 102, for completing initial data acquisition and incremental data from social security data to training data
Acquisition；
Training data memory module 103, for training data to be saved as to the sample data needed for model training, to be formed
Tranining database；
Model training module 104, for the study that exercises supervision to the sample data after presorting, to build prediction model；
Prediction effect tracking module 106, based on the prediction effect of incremental data verification prediction model, if prediction model is pre-
It is not good enough under true environment to survey effect, then trigger model training mission, and model optimization instruction is carried out based on sample data after update
Practice, to build better prediction model.
Preferably, the system comprises data source modules 101, for preserving prefectures and cities' social security industry in social security service database
Business data, to form the primary data of prediction model.
Preferably, the data acquisition module 102 includes initial data acquisition module 1021 and incremental data acquisition module
1022；The initial data acquisition module 1021, for for the first time that the primary data in social security service database is disposably initial
It imports in tranining database；Incremental data acquisition module 1022, for periodically extracting the incremental data in data source modules 101
In converting input tranining database.
Preferably, the model training module 104 includes：
Model training definition module 1041, for defining the training mission of built prediction model；
Model construction task scheduling modules 1042, for receiving model training request, and Boot Model training mission；
Sample is presorted module 1043, for presorting to training sample；
Prediction model training module 1044, exercise supervision to training sample data after presorting study.
Preferably, the system also includes prediction model memory module 105, for storing the prediction model of structure.
Preferably, the prediction effect tracking module 106 includes：
Predicting tracing configuration module 1061 for adding modelling effect tracing task, starts incremental data acquisition tasks, if
Put the rule of trigger model reconstruct；
Prediction result computing module (1062), for according to newly generated incremental data, calling prediction model memory module
(105) prediction model in calculates prediction result；
Prediction effect analysis module 1063, for prediction result and actual value to be compared and analyzed, testing model is true
Prediction effect under real environment, when forecast result of model is unstable, trigger model training mission, re-optimization training prediction mould
Type.
Preferably, the system also includes system prediction recruitment evaluation report generation module (107), for being generated according to new
Incremental data, verify prediction model effect, generate forecast result of model analysis report, to show, analyze and evaluation model
True predictive ability.
(3) advantageous effect
The present invention has following advantageous effect：
1) system forms modeling sample data using prefectures and cities' social security business datum as data source by data extraction tool,
Hospitalization cost prediction model is obtained by machine learning algorithm training sample data, realizes that medical insurance is hospitalized the prediction of correlative charges,
Such as expense distribution situation occurs for the possibility of medical insurance total cost, allowable expense, expense of thinking highly of oneself etc.；
2) system is based on endlessly truthful data, i.e., newly-increased data track prediction effect, and Continuous optimization is realized most
Excellent model construction system is prefectures and cities, various disease rapid build medical insurance hospitalization cost prediction models, ensures that model is located always
In current optimum state, thirst for knowing the following demand that expense situation may occur before solving patient's hospitalization.
Description of the drawings
Fig. 1 is the method flow diagram of prediction model of the present invention；
Fig. 2 is the system structure diagram of prediction model of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 2, the embodiment of the present invention discloses a kind of system for establishing medical insurance hospitalization cost prediction model, including data source
Module 101 and model training systems, wherein, model training systems include data acquisition module 102, training data memory module
103rd, model training module 104, prediction model memory module 105, prediction effect tracking module 106 and evaluation report
Generation module 107.
Data source modules 101, for providing the primary data of prediction model structure；
Data acquisition module 102, for completing initial data acquisition and incremental data from social security data to training data
Acquisition；
Training data memory module 103, for training data to be saved as to the sample data needed for model training；
Model training module 104, for defining, starting and performing model training task, i.e., to the sample number after presorting
According to the study that exercises supervision, to build prediction model；
Prediction model memory module 105, for storing the prediction model of structure；
Prediction effect tracking module 106, based on incremental data verification forecast result of model, if forecast result of model is true
It is not good enough under environment, then trigger model training mission, and model optimization training is carried out based on sample data after update；
Evaluation report generation module 107, for according to newly generated incremental data, verification prediction model effect
Fruit generates forecast result of model analysis report, to show, analyze and the true predictive ability of evaluation model.
Hereinafter, above-mentioned each module will be described one by one.
Including social security service database, prefectures and cities' social security business number is preserved in social security service database for data source modules 101
According to the primary data that as prediction model is built provides data source for model training sample.Prefectures and cities' social security business datum,
Such as medical insurance total cost, allowable expense, expense of thinking highly of oneself.
Data acquisition module 102, is responsible for initial data acquisition and incremental data acquires the acquisition of two item datas, wherein, from society
It protects in service database and acquires primary data and incremental data, primary data are periodically acquired from social security service database 101
Build the training sample database of model training needs jointly with incremental data.Data acquisition module 102 is adopted including primary data
Collect module 1021 and incremental data acquisition module 1022.
Initial data acquisition module 1021, for for the first time disposably initially leading the primary data in social security service database
Enter in tranining database；
Incremental data acquisition module 1022, for the incremental data in data source modules 101 periodically to be extracted converting input
In tranining database.
Training data memory module 103 realizes conversion of the training data to sample data, to form training sample data
Library.Data contained by training sample database include at least：Age, insurant classification, treatment personnel classification, gives special care to pair at gender
As classification, medical treatment classification, therapeutic modality, personal medical year are planned as a whole in classification, lonely classification, crowd's classification, unit property, medical treatment
The characteristic information relevant with hospitalization cost such as degree, this year hospitalizations, medical treatment hospital name, hospital grade, mode of admission and
Corresponding length of stay actually occurs total cost, reimbursed sum, the individual burden amount of money, drug expense, diagnosis and treatment expense, service facility
Cost informations and the reimbursement information such as take.
Model training module 104, for defining, starting and performing model training task, i.e., to the training sample after presorting
Training sample data in database exercise supervision study, to build prediction model.
Model training module 104 includes：
Model training definition module 1041, for defining the training mission of built prediction model, including prediction model districts and cities,
Prediction model expense category, sample are presorted method, model accuracy rate, model-fitting degree, model complexity requirement etc..
Model construction task scheduling modules 1042, for receiving model training request and Boot Model training mission.
Sample is presorted module 1043, for presorting to training sample, i.e., adds class label to training sample.
Method of presorting is classified including clustering algorithm, is classified by expense section, by expense distributive sorting etc., but is not limited to the above method.
Prediction model training module 1044, exercise supervision to training sample data after presorting study, and learning algorithm includes
Neural network, multivariate logistic regression, support vector machines by continuous iterative learning, ultimately form and meet pre-defined fitting
Degree, the prediction model of accuracy rate requirement.
Prediction model memory module 105 preserves the modeling result of prediction model, including preserving prediction model, prediction model
The information such as parameter, prediction model evaluation index.
Prediction effect tracking module 106 includes：
Predicting tracing configuration module 1061 for adding modelling effect tracing task, starts incremental data acquisition tasks, if
The rule of trigger model reconstruct is put, rule includes the judgement of model prediction number of errors and judges with error rate threshold.
Prediction result computing module 1062 for calling the prediction model in prediction model memory module 105, calculates increment
The prediction result of data.Wherein, incremental data is the incremental data being stored in tranining database.
Prediction effect analysis module 1063, is mainly responsible for and prediction result and actual value is compared and analyzed, testing model
Prediction effect under true environment, when forecast result of model is unstable, trigger model builds the model of task scheduling modules
Training mission carries out model optimization, adjusts over-fitting parameter, based on sample data after update, re-optimization training prediction model.
Evaluation report generation module 107 according to the Continuous optimization step of above-mentioned 101-106, is periodically generated mould
Type prediction effect analysis report, to evaluate the true predictive ability of medical insurance hospitalization cost prediction model.
Referring to Fig. 1, the embodiment of the present invention discloses a kind of method for establishing medical insurance hospitalization cost prediction model simultaneously, before utilization
That states establishes medical insurance hospitalization cost forecasting model system, and the above method includes prediction model initial construction process and prediction model is held
Continuous optimization process：
Prediction model initial construction process based on the primary data of social security data, as initial sample data, passes through machine
Learning algorithm builds expense forecast of distribution model, wherein, above-mentioned machine learning algorithm includes clustering algorithm, neural network is calculated
Method, support vector machines, multivariate logistic regression etc..
Prediction model Continuous optimization process, to increasing data newly, progress Cost Forecast compares prediction result and truth,
Obtain forecast result of model, prediction effect bad situation unstable for model, timely Boot Model training mission, adjustment
Over-fitting parameter carries out model optimization training based on sample data after update.
Prediction model initial construction process includes：
Acquire primary data：The primary data of social security data is extracted, forms initial training sample, and preserve to training data
In library；
Training pattern：It is defined according to model training, transfers initial training sample in tranining database, be started and carried out model
Training mission trains initial sample to build prediction model for the first time and store by machine learning algorithm.
Prediction model Continuous optimization process includes：
Acquire incremental data：The incremental data of taken at regular intervals social security data, and preserve into tranining database；
Optimize training pattern：According to the forecast result of model of incremental data verification prediction model, the model prediction that will be obtained
As a result it is compared with actual value, retriggered and Boot Model training mission is determined whether according to reduced value gap size, led to
Sample data after machine learning algorithm optimization training updates is crossed, to build better prediction model and storage.
Generate evaluation report：Based on newly generated incremental data prediction effect, it is periodically generated model prediction effect
Fruit analysis report, to show, analyze and the true predictive ability of evaluation model.
Above system and method are based on endlessly truthful data, i.e., newly-increased data are tracked prediction effect, continued excellent
Change, realize optimal model construction system, be prefectures and cities, various disease rapid build medical insurance hospitalization cost prediction models, ensure
Model is constantly in current optimum state, thirsts for knowing the following need that expense situation may occur before solving patient's hospitalization
It asks.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any this practical relationship or sequence.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those
Element, but also including other elements that are not explicitly listed or further include as this process, method, article or equipment
Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (10)
1. a kind of method for establishing medical insurance hospitalization cost prediction model, holds including prediction model initial construction process and prediction model
Continuous optimization process, which is characterized in that the prediction model Continuous optimization process includes：
Acquire incremental data：The incremental data of taken at regular intervals social security data, and preserve into tranining database；
Optimize training pattern：It is according to the forecast result of model of the previous version prediction model of incremental data verification, obtained model is pre-
It surveys result to be compared with actual value, retriggered and Boot Model training mission is determined whether according to reduced value gap size,
Sample data after training updates is optimized by machine learning algorithm, to build better prediction model and storage.
2. a kind of method for establishing medical insurance hospitalization cost prediction model according to claim 1, which is characterized in that described pre-
Model initial construction process is surveyed to include：
Acquire primary data：The primary data of social security data is extracted, forms initial training sample, and preserve to tranining database
In；
Training pattern：It is defined according to model training, transfers initial training sample in tranining database, be started and carried out model training
Task trains initial sample to build prediction model for the first time and store by machine learning algorithm.
A kind of 3. method for establishing medical insurance hospitalization cost prediction model according to claim 1, which is characterized in that the side
Method further includes generation evaluation reporting process：According to newly generated incremental data, prediction model effect is verified, it is periodically raw
Into forecast result of model analysis report, to show, analyze and the true predictive ability of evaluation model.
4. a kind of system for establishing medical insurance hospitalization cost prediction model, which is characterized in that the system comprises：
Data acquisition module (102) is adopted for completing initial data acquisition from social security data to training data and incremental data
Collection；
Training data memory module (103), for training data to be saved as to the sample data needed for model training, to form instruction
Practice database；
Model training module (104), for the study that exercises supervision to the training sample data after presorting, to build prediction mould
Type；
Prediction effect tracking module (106), based on the prediction effect of incremental data verification prediction model, if the prediction of prediction model
Effect is not good enough under true environment, then trigger model training mission, and carries out model optimization training based on sample data after update,
To build better prediction model.
5. a kind of system for establishing medical insurance hospitalization cost prediction model according to claim 4, it is characterised in that：The system
System includes data source modules (101), for preserving prefectures and cities' social security business datum in social security service database, to form prediction mould
The primary data of type.
6. a kind of system for establishing medical insurance hospitalization cost prediction model according to claim 5, it is characterised in that：The number
Include initial data acquisition module (1021) and incremental data acquisition module (1022) according to acquisition module (102)；The initial number
According to acquisition module (1021), for the primary data in social security service database disposably initially to be imported tranining database for the first time
In；Incremental data acquisition module (1022), for the incremental data in data source modules (101) periodically to be extracted converting input instruction
Practice in database.
7. a kind of system for establishing medical insurance hospitalization cost prediction model according to claim 4, it is characterised in that：The mould
Type training module (104) includes：
Model training definition module (1041), for defining the training mission of built prediction model；
Model construction task scheduling modules (1042), for receiving model training request, and Boot Model training mission；
Sample is presorted module (1043), for presorting to training sample；
Prediction model training module (1044), exercise supervision to training sample data after presorting study.
8. a kind of system for establishing medical insurance hospitalization cost prediction model according to claim 4, it is characterised in that：The system
System further includes prediction model memory module (105), for storing the prediction model of structure.
9. a kind of system for establishing medical insurance hospitalization cost prediction model according to claim 8, it is characterised in that：It is described pre-
Effect tracking module (106) is surveyed to include：
Predicting tracing configuration module (1061) for adding modelling effect tracing task, starts incremental data acquisition tasks, setting
The rule of trigger model reconstruct；
Prediction result computing module (1062), for according to newly generated incremental data, calling prediction model memory module (105)
In prediction model calculate prediction result；
Prediction effect analysis module (1063), for prediction result and actual value to be compared and analyzed,
Prediction effect of the testing model under true environment, when forecast result of model is unstable, trigger model training mission, weight
New optimization training prediction model.
10. according to a kind of system for establishing medical insurance hospitalization cost prediction model of claim 4-9 any one of them, feature exists
In：The system also includes system prediction recruitment evaluation report generation module (107), for according to newly generated incremental data,
It verifies prediction model effect, generates forecast result of model analysis report, to show, analyze and the true predictive energy of evaluation model
Power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471828.5A CN108197737A (en) | 2017-12-29 | 2017-12-29 | A kind of method and system for establishing medical insurance hospitalization cost prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711471828.5A CN108197737A (en) | 2017-12-29 | 2017-12-29 | A kind of method and system for establishing medical insurance hospitalization cost prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108197737A true CN108197737A (en) | 2018-06-22 |
Family
ID=62586335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711471828.5A Pending CN108197737A (en) | 2017-12-29 | 2017-12-29 | A kind of method and system for establishing medical insurance hospitalization cost prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197737A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898504A (en) * | 2018-07-09 | 2018-11-27 | 北京精友世纪软件技术有限公司 | The intelligent training and improving method of loss assessment system are surveyed in a kind of movement |
| CN109101259A (en) * | 2018-08-28 | 2018-12-28 | 郑州云海信息技术有限公司 | A kind of update method, device and the terminal of OSDMap caching container |
| CN109492829A (en) * | 2018-12-13 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance fund expenditure prediction technique and relevant apparatus based on artificial intelligence |
| CN109492803A (en) * | 2018-10-30 | 2019-03-19 | 平安科技（深圳）有限公司 | Chronic disease hospitalization cost method for detecting abnormality and relevant apparatus based on artificial intelligence |
| CN109598378A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical insurance prediction technique, device, equipment and computer readable storage medium |
| CN109598302A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical expenditure prediction technique, device, equipment and computer readable storage medium |
| CN109712008A (en) * | 2018-12-20 | 2019-05-03 | 泰康保险集团股份有限公司 | Declaration form processing method, device, medium and electronic equipment |
| CN109887590A (en) * | 2019-02-21 | 2019-06-14 | 广州天鹏计算机科技有限公司 | Cost Forecast method, apparatus, computer equipment and the storage medium of medical item |
| CN109934412A (en) * | 2019-03-18 | 2019-06-25 | 无锡雪浪数制科技有限公司 | Real-time device abnormal detector and method based on Time series forecasting model |
| CN109992473A (en) * | 2019-02-27 | 2019-07-09 | 平安科技（深圳）有限公司 | Monitoring method, device, equipment and the storage medium of application system |
| CN111096735A (en) * | 2018-10-26 | 2020-05-05 | 深圳市理邦精密仪器股份有限公司 | Electrocardiogram analysis system capable of being updated iteratively |
| CN112183861A (en) * | 2020-09-28 | 2021-01-05 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN112289424A (en) * | 2020-12-30 | 2021-01-29 | 曜立科技(北京)有限公司 | Intelligent report automatic generation method and system based on operation fee control |
| CN113705930A (en) * | 2021-09-16 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Model-based cost prediction method and device, computer equipment and storage medium |
| CN117349676A (en) * | 2023-12-05 | 2024-01-05 | 神州医疗科技股份有限公司 | Model training method and system based on mq port and redis database |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8108243B2 (en) * | 2004-06-18 | 2012-01-31 | Cvidya Networks | Methods, systems and computer readable code for forecasting time series and for forecasting commodity consumption |
| CN103971170A (en) * | 2014-04-17 | 2014-08-06 | 北京百度网讯科技有限公司 | Method and device for forecasting changes of feature information |
| CN106202986A (en) * | 2016-09-28 | 2016-12-07 | 湖南老码信息科技有限责任公司 | A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system |
| CN106250712A (en) * | 2016-09-28 | 2016-12-21 | 湖南老码信息科技有限责任公司 | A kind of ureteral calculus Forecasting Methodology based on increment type neural network model and prognoses system |
| CN106295238A (en) * | 2016-09-28 | 2017-01-04 | 湖南老码信息科技有限责任公司 | A kind of hypertensive nephropathy Forecasting Methodology based on increment type neural network model and prognoses system |
| CN107133699A (en) * | 2017-05-12 | 2017-09-05 | 百度国际科技（深圳）有限公司 | Box office receipts trend forecasting method and device, equipment, storage medium |
-
2017
- 2017-12-29 CN CN201711471828.5A patent/CN108197737A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8108243B2 (en) * | 2004-06-18 | 2012-01-31 | Cvidya Networks | Methods, systems and computer readable code for forecasting time series and for forecasting commodity consumption |
| CN103971170A (en) * | 2014-04-17 | 2014-08-06 | 北京百度网讯科技有限公司 | Method and device for forecasting changes of feature information |
| CN106202986A (en) * | 2016-09-28 | 2016-12-07 | 湖南老码信息科技有限责任公司 | A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system |
| CN106250712A (en) * | 2016-09-28 | 2016-12-21 | 湖南老码信息科技有限责任公司 | A kind of ureteral calculus Forecasting Methodology based on increment type neural network model and prognoses system |
| CN106295238A (en) * | 2016-09-28 | 2017-01-04 | 湖南老码信息科技有限责任公司 | A kind of hypertensive nephropathy Forecasting Methodology based on increment type neural network model and prognoses system |
| CN107133699A (en) * | 2017-05-12 | 2017-09-05 | 百度国际科技（深圳）有限公司 | Box office receipts trend forecasting method and device, equipment, storage medium |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898504A (en) * | 2018-07-09 | 2018-11-27 | 北京精友世纪软件技术有限公司 | The intelligent training and improving method of loss assessment system are surveyed in a kind of movement |
| CN108898504B (en) * | 2018-07-09 | 2021-12-07 | 北京精友世纪软件技术有限公司 | Intelligent training and improving method for mobile survey damage assessment system |
| CN109101259A (en) * | 2018-08-28 | 2018-12-28 | 郑州云海信息技术有限公司 | A kind of update method, device and the terminal of OSDMap caching container |
| CN109101259B (en) * | 2018-08-28 | 2021-07-16 | 郑州云海信息技术有限公司 | Updating method and device of OSDMap cache container and terminal |
| CN111096735A (en) * | 2018-10-26 | 2020-05-05 | 深圳市理邦精密仪器股份有限公司 | Electrocardiogram analysis system capable of being updated iteratively |
| CN109492803A (en) * | 2018-10-30 | 2019-03-19 | 平安科技（深圳）有限公司 | Chronic disease hospitalization cost method for detecting abnormality and relevant apparatus based on artificial intelligence |
| CN109598302B (en) * | 2018-11-30 | 2022-11-15 | 平安医疗健康管理股份有限公司 | Method, device and equipment for predicting treatment cost and computer readable storage medium |
| CN109598302A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical expenditure prediction technique, device, equipment and computer readable storage medium |
| CN109598378A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical insurance prediction technique, device, equipment and computer readable storage medium |
| CN109492829A (en) * | 2018-12-13 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance fund expenditure prediction technique and relevant apparatus based on artificial intelligence |
| CN109712008A (en) * | 2018-12-20 | 2019-05-03 | 泰康保险集团股份有限公司 | Declaration form processing method, device, medium and electronic equipment |
| CN109887590A (en) * | 2019-02-21 | 2019-06-14 | 广州天鹏计算机科技有限公司 | Cost Forecast method, apparatus, computer equipment and the storage medium of medical item |
| CN109992473B (en) * | 2019-02-27 | 2022-07-15 | 平安科技（深圳）有限公司 | Application system monitoring method, device, equipment and storage medium |
| CN109992473A (en) * | 2019-02-27 | 2019-07-09 | 平安科技（深圳）有限公司 | Monitoring method, device, equipment and the storage medium of application system |
| CN109934412A (en) * | 2019-03-18 | 2019-06-25 | 无锡雪浪数制科技有限公司 | Real-time device abnormal detector and method based on Time series forecasting model |
| CN112183861A (en) * | 2020-09-28 | 2021-01-05 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN112183861B (en) * | 2020-09-28 | 2024-01-26 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN112289424A (en) * | 2020-12-30 | 2021-01-29 | 曜立科技(北京)有限公司 | Intelligent report automatic generation method and system based on operation fee control |
| CN113705930A (en) * | 2021-09-16 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Model-based cost prediction method and device, computer equipment and storage medium |
| CN117349676A (en) * | 2023-12-05 | 2024-01-05 | 神州医疗科技股份有限公司 | Model training method and system based on mq port and redis database |
| CN117349676B (en) * | 2023-12-05 | 2024-03-12 | 神州医疗科技股份有限公司 | Model training method and system based on mq port and redis database |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197737A (en) | A kind of method and system for establishing medical insurance hospitalization cost prediction model | |
| Altuntas et al. | Analysis of patent documents with weighted association rules | |
| Morid et al. | Learning hidden patterns from patient multivariate time series data using convolutional neural networks: A case study of healthcare cost prediction | |
| CN106067079A (en) | A kind of system and method for gray haze based on BP neutral net prediction | |
| CN104572709A (en) | Data mining system used for enterprise innovation system | |
| CN105809277A (en) | Big data based prediction method for the refining and managing of electric power marketing inspection | |
| Van et al. | Research trends on machine learning in construction management: a scientometric analysis | |
| CN107145723A (en) | Hospital process management system based on artificial neural network | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| CN108416524A (en) | Estate planning based on a figure general framework refines deciphering method | |
| CN110033191B (en) | Business artificial intelligence analysis method and system | |
| Aghimien et al. | A review of the application of data mining for sustainable construction in Nigeria | |
| Massaro | Implementation of a decision support system and business Intelligence algorithms for the automated management of insurance agents activities | |
| Ammar et al. | Departments of transportation efforts to digitize ancillary transportation asset data: a step toward digital twins | |
| Chen et al. | A new data envelopment analysis clustering approach within cross-efficiency framework | |
| Bâra et al. | Improving decision support systems with data mining techniques | |
| CN110335160A (en) | A kind of medical treatment migratory behaviour prediction technique and system for improving Bi-GRU based on grouping and attention | |
| CN117350775A (en) | Medical surgical robot market current situation demand analysis method and system | |
| CN117114269A (en) | Strategic performance management system for implementing development strategy process in villages and towns | |
| CN116416090A (en) | Spatial correlation network characteristic acquisition method and system for carbon emission efficiency in thermal power industry | |
| Tytenko et al. | Software and information support for business analysis in enterprise management | |
| Binsar et al. | Drug stock optimization based on consumption patterns for hospital formulary using deep learning approach | |
| CN114678126A (en) | Disease tracking and predicting system | |
| Warestika et al. | Business intelligence design for data visualization and drug stock forecasting | |
| Badinelli et al. | Integrating the internet of things and big data analytics into decision support models for healthcare management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |