CN106326642A - Method for establishing medical consultation fee lattice model based on big data analysis - Google Patents
Method for establishing medical consultation fee lattice model based on big data analysis Download PDFInfo
- Publication number
- CN106326642A CN106326642A CN201610673805.1A CN201610673805A CN106326642A CN 106326642 A CN106326642 A CN 106326642A CN 201610673805 A CN201610673805 A CN 201610673805A CN 106326642 A CN106326642 A CN 106326642A
- Authority
- CN
- China
- Prior art keywords
- value
- data
- point
- utility
- distance
- 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
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a method for establishing a medical consultation fee lattice model based on big data analysis. The method comprises the following steps: step 1, acquiring data in a fee original table; step 2, pre-processing the data: converting recorded values of all charging items in the fee original table into quantification values; carrying out summation calculation on the quantification values of a same charging item of one patient, and storing processed data into a quantification value table; step 3, carrying out cluster analysis on the pre-processed data by adopting a multi-index abnormal data digging technology based on a distance, and digging out noise points in data records. According to the method provided by the invention, rare data is digged out through establishing the model aiming at medical consultation fees to carry out data analysis, and abnormal behaviors of off-group points are researched; various types of disease symptoms, treatment items accepted by people, prescription drugs and charging are analyzed; item points with abnormal charging are found out and reference is provided for clinical drug of doctors and reasonable charging, so that the doctors are supervised and urged to insist on reasonable drug administration, reasonable checking, reasonable treatment and reasonable charging.
Description
Technical field
The present invention relates to consultation fee abnormality detection technical field, particularly relate to set up medical treatment consultation fee dot matrix based on big data analysis
The method of model.
Background technology
Nowadays the common people have blame to medical system more, the problem such as especially make unwarranted inspections, disorderly write a prescription.Doctor makes unwarranted inspections, unrest is opened
The wallet of the common people not only hindered by medicine, wastes China originally with regard to limited medical resource, is also the irresponsibility healthy to the common people.Right
It is patient, hospital, the hot issue of administration section's care that medical expense effectively, in time, comprehensively monitors, and directly affects medical treatment matter
Amount and the development of medical treatment & health, timely and effective monitoring management all sidedly, contribute to Perfecting Supervision mechanism, to setting up effective hospital
Administrative mechanism, improves Hospital Competitiveness, plays a role in promoting.For the monitoring of medical expense be researchers' general concern and
The problem paid attention to.
Summary of the invention
It is desirable to provide based on big data analysis set up medical treatment consultation fee lattice model method, can excavate find out rare
Data, find out abnormal charging item point.
For achieving the above object, the technical solution used in the present invention is as follows:
The method setting up medical treatment consultation fee lattice model based on big data analysis, comprises the following steps:
Step 1, obtains the data in expense original table；Patient ID, each charging item, and the record of the charging item amount of money
Value；
Step 2, data prediction: the record value of the amount of money of charging item each in expense original table is converted into quantized value,
Then the quantized value to the identical charging item of same patient carries out read group total, and the data after processing are stored in quantization
In value table；
Step 3, uses the Outlier mining technology of multi objective based on distance to carry out the data after data prediction
Cluster analysis, excavates the hot-tempered point in data record.
Further, also include step 4, utilize the scatterplot control of echart, the hot-tempered point excavated is associated, exhibition
Abnormal data in cost of medical service is shown.
Further, quantized value is converted to value of utility by described step 2 in the following ways, it is assumed that quantization value table has
N bar record, each record value of t field is: Xst, wherein s=1,2 ..., n；T=1,2 ..., m；N is line number, and m is row
Number；
Mode 1: be the bigger the better type, remembers Xtmax=max{Xst},XTmin=min { XSt), wherein 1≤s≤n, by XstTurn
Turn to Xst～,Maximum is converted into value of utility 1, and minima is converted into value of utility 0；
Mode 2: the smaller the better type, thenMinima is converted into value of utility 1, and maximum turns
Turn to value of utility 0；
Mode 3: moderate type, remembers that optimal moderate value is X0。
ThenNow close to moderate value data value of utility relatively
Greatly, close to 1, away from the value of utility of data less, close to 0.
Further, described step 3 specifically includes following steps:
Step 3.1, uses formula (1) to calculate the distance between each effectiveness point:
In formula (1), DkFor the distance between effectiveness point, XpiFor the value of utility of pth row the i-th row, XqiIt is q row the i-th row
Value of utility；1 ＜ ＜ p ＜ ＜ n, 1 ＜ ＜ q ＜ ＜ n；N is line number, and m is columns；
Step 3.2, for effectiveness point p, all meets DkThe point of ＜ δ constitutes the δ field of effectiveness point p, and δ is given one
Positive number；
Step 3.3, adds up Np, NpFor the number of effectiveness point in described field；
Step 3.4, if Np＜ N0, then this effectiveness point p is the abnormity point under distance sense, N0For given marginal value.
Further, by DkIt is stored in distance table, sets δ and N0, table of adjusting the distance carries out twice nested scan, outer layer
Scanning is carried out from top to bottom, and internal layer scanning is carried out from left to right, adds up every a line DkThe number of ＜ δ, if Np＜ N0, then this point is
Abnormity point；Otherwise, subsequent cycle is entered.
Further, k=2, δ=3, N0=5.
The method have the advantages that
The present invention is directed to medical treatment consultation fee and set up model data analysis, find out those by outlier mining and most of objects have
The rare data of very different behavior, the Deviant Behavior of research outlier, analyze all kinds of disease, the treatment item of crowd's acceptance
Mesh, prescriptions and charge, find out abnormal charging item point, and the expense exception scatterplot of formation can be Hospital Decision making layer-management
Doctor's clinical application and reasonable fee provide reference, thus supervise doctor to adhere to rational use of drug, legitimate check, rational therapy, conjunction
Reason charge.
Accompanying drawing explanation
Fig. 1 is the quantization value table of gastric abscess consultation fee；
Fig. 2 is the value of utility table of gastric abscess consultation fee；
Fig. 3 is the distance table of gastric abscess consultation fee；
Fig. 4 is expense abnormality detection scatterplot.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing, the present invention is made
Further describe.
It is the core merit building medical consultation fee lattice model based on big data analysis that big Data Analysis Platform processes framework
Can, set up big data acquisition platform, use the medical data acquisition technology of cloud computing mode, gather the clinical disease of 80 multiple hospitals
Go through data, data acquisition xml document formal layout, it is provided that unify, upload interface easily, support that real-time files disposition is looked into
Ask, upload batch management and problem data rollback.The most compatible other data format analysis processing and interface sides.By gathering number
According to pretreatment ETL (clean, change, the load) operation of, it is provided that clinical data, build big data distributed Hadoop cluster, point
Cloth storage and calculating；The calculating of row laggard to the Data Integration data mining algorithm such as stream calculation, it is achieved medical treatment consultation fee dot matrix should
Use model.Wherein data cleansing, is one and reduces mistake and discordance, the process of solution Object identifying, including checking data
Concordance, processes invalid value and missing values etc.；Conversion is to be substantially carried out inconsistent data conversion, including data form, writes by mistake
Deng.Change to ensure the accuracy of data, be converted to target data structure, it is achieved collect, and load data warehouse.
The techniqueflow of the present invention is: cleans data, carries out ETL Data Integration classification by disease, crowd；Set up pattern number
According to analysis, carry out Outliers Detection based on clustering algorithm, find out those by outlier mining and most of objects have very different
The rare data of behavior, the Deviant Behavior of research outlier, analyze all kinds of disease, the treatment project of crowd's acceptance, prescriptions
And charge, find out abnormal charging item point.
The method setting up medical treatment consultation fee lattice model based on big data analysis disclosed by the invention, at above-mentioned big data analysis
On the basis of platform processes framework, use clustering method, carry out Outliers Detection, find abnormity point.Further profit on the basis of this
By the form of scatterplot, represent the prescription charge situation of doctor.
Embodiment 1
The method setting up medical treatment consultation fee lattice model based on big data analysis, comprises the following steps:
Step 1, obtains the data in expense original table；Patient ID, each charging item, and the record of the charging item amount of money
Value；
Step 2, data prediction: the record value of the amount of money of charging item each in expense original table is converted into quantized value,
Then the quantized value to the identical charging item of same patient carries out read group total, and the data after processing are stored in quantization
In value table.Such as, there is nonstandard phenomenon in the record value in expense original table, such as " 35 yuan ", so this step is by " 35 yuan "
It is converted into quantized value " 35 ".
Step 3, uses the Outlier mining technology of multi objective based on distance to carry out the data after data prediction
Cluster analysis, excavates the hot-tempered point in data record.
Further, also include step 4, utilize the scatterplot control of echart, the hot-tempered point excavated is associated, exhibition
Abnormal data in cost of medical service is shown.
For ease of calculating, the most in the following ways quantized value is converted to value of utility,.Assume in quantization value table
Having n bar record, each record value of t field is: Xst, wherein s=1,2 ..., n；T=1,2 ..., m；N is line number, and m is
Columns；
Mode 1: be the bigger the better type, remembers Xtmax=max{Xst},Xtmin=min{Xst, wherein 1≤s≤n, by XstIt is converted into
Xst～,Maximum is converted into value of utility 1, and minima is converted into value of utility 0；
Mode 2: the smaller the better type, thenMinima is converted into value of utility 1, and maximum turns
Turn to value of utility 0；
Mode 3: moderate type, remembers that optimal moderate value is X0。
ThenNow close to moderate value data value of utility relatively
Greatly, close to 1, away from the value of utility of data less, close to 0.
Step 3 specifically includes following steps:
Step 3.1, uses formula (1) to calculate the distance between each effectiveness point:
In formula (1), DkFor the distance between effectiveness point, XpiFor the value of utility of pth row the i-th row, XqiIt is q row the i-th row
Value of utility；1 ＜ ＜ p ＜ ＜ n, 1 ＜ ＜ q ＜ ＜ n；N is line number, and m is columns.Certainly, without quantized value being converted to effect
By value, then the X in formula (1)piCan be the quantized value of pth row the i-th row, XqiIt is the quantized value of q row the i-th row, the most also
It is to calculate the distance between data point.The general value of k is 2.
Step 3.2, for effectiveness point p, all meets DkThe point of ＜ δ constitutes the δ field of effectiveness point p, and δ is given one
Positive number；
Step 3.3, adds up Np, NpFor the number of effectiveness point in described field；
Step 3.4, if Np＜ N0, then this effectiveness point p is the abnormity point under distance sense, N0For given marginal value.
Further, by DkIt is stored in distance table, sets δ and N0, table of adjusting the distance carries out twice nested scan, outer layer
Scanning is carried out from top to bottom, and internal layer scanning is carried out from left to right, adds up every a line DkThe number of ＜ δ, if Np＜ N0, then this point is
Abnormity point；Otherwise, subsequent cycle is entered.
Embodiment 2
The present embodiment is as a example by the medical consultation fee of gastric abscess, and the present invention will be described in detail.
Obtain the data in the expense original table of certain time period certain age bracket gastric abscess patient；By in expense original table
The record value of the amount of money of each charging item is converted into quantized value, then enters the quantized value of the identical charging item of same patient
Row read group total, and will process after data be stored in quantization value table, the gauge outfit of quantization value table includes patient ID and respectively charges
The title of project；The quantization value table of gastric abscess consultation fee as shown in Figure 1；
Quantized value in quantization value table is converted to value of utility, obtains value of utility table as shown in Figure 2, the table of value of utility table
Head includes patient ID and the title of each charging item；Then scanning value of utility table, uses formula (1) to calculate in value of utility table and respectively imitates
By the distance between point.Because record strip quantity is big, therefore, distance parameter is separately existed in distance table as shown in Figure 3.
For ease of analyzing various different situations, set smaller positive number δ=3 and a given empirical threshold value
N0=5, in distance table, carry out twice nested scan.Outer layer scanning is carried out from top to bottom, and internal layer scanning is carried out from left to right, right
The number of every a line statistical distance d ＜ δ, if less than set-point N0, then can determine whether that this point is abnormity point.Otherwise, enter next to follow
Ring.Owing to can at random revise radius δ and marginal value N of neighborhood0, the most only need to call distance parameter table and phase need not be calculated
Distance between Hu.So can dynamically determine the abnormity point under different field radiuses and marginal value meaning.
In radius of neighbourhood δ=3 and empirical threshold value N0In the case of=5, excavate 19 abnormity point, i.e. 19 patients.
The exception of these patients refers to that their expense differs greatly for other patients.
Utilize the scatterplot control of echart, the hot-tempered point excavated is associated, shows the exception in cost of medical service
Data, expense abnormality detection scatterplot is as shown in Figure 4.In Fig. 4, vertical coordinate is the treatment mean treatment expense that doctor writes a prescription out single
(unit: unit), abscissa is the distribution in doctor hospital area, and round dot size represents physician visits number situation, and round dot region is more
Deviation, illustrates that doctor averagely charges the highest.By expense abnormality detection scatterplot, doctor place hospital can not only be seen, moreover it is possible to
See average charge and Maximum Charge, and diagnosis and treatment number.
The present invention electronic health record by Real-time Collection hospital, to more than 30 ten thousand case histories of 80 multiple hospitals by disease, crowd
Classifying, utilize clustering algorithm, carry out Outliers Detection, the expense exception scatterplot of formation can be Hospital Decision making layer-management doctor
Raw clinical application and reasonable fee provide reference.From largely supervising doctor to adhere to rational use of drug, legitimate check, rationally control
Treatment, reasonable fee.
Certainly, the present invention also can have other numerous embodiments, in the case of without departing substantially from present invention spirit and essence thereof,
Those of ordinary skill in the art can make various corresponding change and deformation according to the present invention, but these change accordingly and become
Shape all should belong to the protection domain of appended claims of the invention.
Claims (6)
1. the method setting up medical treatment consultation fee lattice model based on big data analysis, it is characterised in that: comprise the following steps:
Step 1, obtains the data in expense original table, and data include each charging item, and the record value of the charging item amount of money；
Step 2, data prediction: the record value of the amount of money of charging item is converted into quantized value, then to same patient's
The quantized value of identical charging item carries out read group total, and the data after processing are stored in quantization value table；
Step 3, uses the Outlier mining technology of multi objective based on distance that pretreated data are carried out cluster analysis,
Excavate the hot-tempered point in data record.
2. the method for claim 1, it is characterised in that: also include step 4, utilize the scatterplot control of echart, will
The hot-tempered point excavated is associated, and shows the abnormal data in cost of medical service.
3. the method for claim 1, it is characterised in that: quantized value is converted to by described step 2 in the following ways
Value of utility, it is assumed that have n bar record in quantization value table, each record value of t field is: Xst, wherein s=1,2 ..., n；T=
1,2,…,m；N is line number, and m is columns；
Mode 1: be the bigger the better type, remembers Xtmax=max{Xst},Xtmin=min{Xst, wherein 1≤s≤n, by XstIt is converted into Xst ~,Maximum is converted into value of utility 1, and minima is converted into value of utility 0；
Mode 2: the smaller the better type, thenMinima is converted into value of utility 1, and maximum is converted into effect
By value 0；
Mode 3: moderate type, remembers that optimal moderate value is X0。
ThenValue of utility now close to the data of moderate value is relatively big, connects
Be bordering on 1, away from the value of utility of data less, close to 0.
4. method as claimed in claim 3, it is characterised in that: described step 3 specifically includes following steps:
Step 3.1, uses formula (1) to calculate the distance between each effectiveness point:
In formula (1), DkFor the distance between effectiveness point, XpiFor the value of utility of pth row the i-th row, XqiIt is the effectiveness of q row the i-th row
Value；1 ＜ ＜ p ＜ ＜ n, 1 ＜ ＜ q ＜ ＜ n；N is line number, and m is columns；
Step 3.2, for effectiveness point p, all meets DkThe point of ＜ δ constitutes the δ field of effectiveness point p, and δ is a given positive number；
Step 3.3, adds up Np, NpFor the number of effectiveness point in described field；
Step 3.4, if Np＜ N0, then this effectiveness point p is the abnormity point under distance sense, N0For given marginal value.
5. method as claimed in claim 4, it is characterised in that: by DkBeing stored in distance table, the gauge outfit of distance table includes, if
Determining δ and N0, carry out twice nested scan in table of adjusting the distance, outer layer scanning is carried out from top to bottom, and internal layer scanning is carried out from left to right,
Add up every a line DkThe number of ＜ δ, if Np＜ N0, then this point is abnormity point；Otherwise, subsequent cycle is entered.
6. the method as described in claim 4 or 5, it is characterised in that: k=2, δ=3, N0=5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610673805.1A CN106326642A (en) | 2016-08-16 | 2016-08-16 | Method for establishing medical consultation fee lattice model based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610673805.1A CN106326642A (en) | 2016-08-16 | 2016-08-16 | Method for establishing medical consultation fee lattice model based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106326642A true CN106326642A (en) | 2017-01-11 |
Family
ID=57739980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610673805.1A Pending CN106326642A (en) | 2016-08-16 | 2016-08-16 | Method for establishing medical consultation fee lattice model based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326642A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133734A (en) * | 2017-12-21 | 2018-06-08 | 广东工业大学 | A kind of analysis method, device and the equipment of medical expense big data |
| CN109543774A (en) * | 2018-12-13 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Abnormal hemodialysis proportion detection method, device, equipment and computer storage medium |
| CN109615377A (en) * | 2018-12-13 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Repetition charge recognition methods, equipment, storage medium and device based on big data |
| CN109801691A (en) * | 2018-12-13 | 2019-05-24 | 平安科技（深圳）有限公司 | Assault based on big data is gone to a doctor recognition methods, equipment, storage medium and device |
| WO2020082791A1 (en) * | 2018-10-22 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Drug cost over-standard risk control method and apparatus based on data processing |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN116052887A (en) * | 2023-03-01 | 2023-05-02 | 联仁健康医疗大数据科技股份有限公司 | Method and device for detecting excessive inspection, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004246622A (en) * | 2003-02-13 | 2004-09-02 | Ntt Data Corp | Outlier detection supporting program, outlier detection supporting method, and outlier detection supporting device |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
-
2016
- 2016-08-16 CN CN201610673805.1A patent/CN106326642A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004246622A (en) * | 2003-02-13 | 2004-09-02 | Ntt Data Corp | Outlier detection supporting program, outlier detection supporting method, and outlier detection supporting device |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
Non-Patent Citations (2)
| Title |
|---|
| 牛晓辉: "《新农合住院费用的分析及异常值筛检方法研究》", 《中国博士学位论文全文数据库 医药卫生科技辑》 * |
| 赵泽茂等: "《基于距离的异常数据挖掘算法及其应用》", 《计算机应用与软件》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133734A (en) * | 2017-12-21 | 2018-06-08 | 广东工业大学 | A kind of analysis method, device and the equipment of medical expense big data |
| WO2020082791A1 (en) * | 2018-10-22 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Drug cost over-standard risk control method and apparatus based on data processing |
| CN109543774A (en) * | 2018-12-13 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Abnormal hemodialysis proportion detection method, device, equipment and computer storage medium |
| CN109615377A (en) * | 2018-12-13 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Repetition charge recognition methods, equipment, storage medium and device based on big data |
| CN109801691A (en) * | 2018-12-13 | 2019-05-24 | 平安科技（深圳）有限公司 | Assault based on big data is gone to a doctor recognition methods, equipment, storage medium and device |
| CN109543774B (en) * | 2018-12-13 | 2022-10-14 | 平安医疗健康管理股份有限公司 | Abnormal hemodialysis ratio detection method, device, equipment and computer storage medium |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN116052887A (en) * | 2023-03-01 | 2023-05-02 | 联仁健康医疗大数据科技股份有限公司 | Method and device for detecting excessive inspection, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326642A (en) | Method for establishing medical consultation fee lattice model based on big data analysis | |
| US8731966B2 (en) | Systems and methods for real-time data ingestion to a clinical analytics platform to generate a heat map | |
| Mishra et al. | Analysis of the role and scope of big data analytics with IoT in health care domain | |
| CN104699985A (en) | Medical big-data acquisition and analysis system and method | |
| Binder et al. | On analyzing process compliance in skin cancer treatment: An experience report from the evidence-based medical compliance cluster (EBMC 2) | |
| DE112014000897T5 (en) | Learning health systems and procedures | |
| CN105528529A (en) | Data processing method of traditional Chinese medicine clinical skill evaluation system based on big data analysis | |
| JP2018170004A (en) | System and method for predicting behavior of new patient | |
| US20160267254A1 (en) | System and method for classifying respiratory and overall health status of an animal | |
| Cheheltani et al. | Predicting misdiagnosed adult-onset type 1 diabetes using machine learning | |
| Maini et al. | Data lake-an optimum solution for storage andanalytics of big data in cardiovascular disease prediction system | |
| Fang et al. | A study on specialist or special disease clinics based on big data | |
| Jain et al. | Big data analysis for prediction of coronary artery disease | |
| Huang et al. | Dimensionality reduction for knowledge discovery in medical claims database: application to antidepressant medication utilization study | |
| Hu | Research on monitoring system of daily statistical indexes through big data | |
| Wang et al. | DensityTransfer: A data driven approach for imputing electronic health records | |
| Kaur et al. | A smart and promising neurological disorder diagnostic system: An amalgamation of big data, IoT, and emerging computing techniques | |
| Adams et al. | The healthcare analytics evolution: moving from descriptive to predictive to prescriptive | |
| Mei et al. | Human disease clinical treatment network for the elderly: analysis of the medicare inpatient length of stay and readmission data | |
| Jiang et al. | Application and Feasibility Study of Integrated Nursing Information Construction in Nephrology Nursing | |
| Tamiziniyan et al. | Future of Healthcare: Biomedical Big Data Analysis and IoMT | |
| Saravanan et al. | Foundation of big data and internet of things: Applications and case study | |
| Jagdev et al. | Implementation and applications of big data in health care industry | |
| Geroski et al. | Big Data in multiscale modelling: from medical image processing to personalized models | |
| Ali et al. | Application of artificial intelligence in monitoring of animal health and welfare |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170111 |
|
| RJ01 | Rejection of invention patent application after publication |