CN113436027A - Medical insurance reimbursement abnormal data detection method and system - Google Patents
Medical insurance reimbursement abnormal data detection method and system Download PDFInfo
- Publication number
- CN113436027A CN113436027A CN202110739794.3A CN202110739794A CN113436027A CN 113436027 A CN113436027 A CN 113436027A CN 202110739794 A CN202110739794 A CN 202110739794A CN 113436027 A CN113436027 A CN 113436027A
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- clustering
- fuzzy
- abnormal data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The disclosure provides a method and a system for detecting medical insurance reimbursement abnormal data, which comprise the following steps: acquiring medical data, and performing data processing including data cleaning and feature extraction; based on the processed data, a fuzzy C-means clustering model is constructed, the medical data to be tested are clustered by using the model, a clustering result is obtained, and suspected abnormal data are output; and pushing the suspected abnormal data, detecting again, and determining whether the data is really abnormal data. The medical personnel clustering method is based on the fuzzy C-means clustering algorithm, and is used for clustering the medical personnel, namely clustering is performed on the patients according to the medical information of the patients, so that the defects of a hard clustering method can be effectively overcome, the medical personnel can not be clustered hard, and the situations of misjudgment and excessive judgment in the detection process are avoided.
Description
Technical Field
The disclosure belongs to the technical field of computers, and particularly relates to a method and a system for detecting medical insurance reimbursement abnormal data.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Since the establishment of a basic medical guarantee system, the coverage is continuously expanded, the guarantee level is stably improved, and the method plays a positive role in maintaining the health rights and interests of people, relieving the poverty caused by diseases and promoting the reform of medical health systems. However, due to the restriction of factors such as an imperfect supervision system, an imperfect detection mechanism and the like, the problem of fraud and cheat insurance is frequently issued, and aiming at the abnormal reimbursement of medical insurance, most of the existing methods are manual detection, the efficiency is too low, and the problems of manual intervention exist.
The abnormal data refers to the data appearing on the patient document when the hospital or medical insurance department staff find that the prescribed medicine belongs to contraindicated medicine of the patient or is not the medicine required for treating the disease at the time, or the quantity of a certain medicine is too high or two medicines cannot be prescribed at the same time due to the medicine property when the hospital or medical insurance department staff manually checks the medical insurance settlement document of the patient, and the data is called abnormal data.
At present, the detection efficiency can be greatly improved by extracting the hospitalizing data and applying a machine learning algorithm to detect the medical insurance reimbursement abnormity, but the application of the machine learning algorithm mostly adopts a hard clustering mode, so that the method is not flexible enough and is easy to be wrongly classified.
Hard clustering means that each sample point must be "not that which is" classified into a cluster. Either 0 or 1 corresponds to a hard cluster to a soft cluster, and for each sample point the soft clustering algorithm calculates the probability that the point belongs to a different cluster, which is a fuzzy concept that does not require a "not-that-other" mapping between sample points and clusters, but rather allows the sample points to belong to different clusters with different probabilities.
The general hard clustering algorithm is K-means clustering and HCM clustering, and the soft clustering comprises fuzzy C-means clustering and GMM (Gaussian mixture model) clustering.
The misgrading of the medical data refers to that the hard clustering is not a judgment method, so that the abnormal data caused by low medical frequency, high medicine cost and other normal reasons of the patient medical insurance settlement documents can be classified as the behavior of cheating medical insurance funds, and the misgrading of the medical data caused by the data processing method exists in the prior art.
Disclosure of Invention
In order to overcome the defects of the prior art, the medical insurance reimbursement abnormal data detection method is provided, the hospitalizing information is clustered, the defects of a hard clustering method can be effectively overcome, the hospitalizing personnel cannot be clustered hard, and the situations of misjudgment and excessive judgment in the detection process are avoided.
In order to achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:
in a first aspect, a method for detecting abnormal data of medical insurance reimbursement is disclosed, comprising:
acquiring medical data, and performing data processing including data cleaning and feature extraction;
based on the processed data, a fuzzy C-means clustering model is constructed, the medical data to be tested are clustered by using the model, a clustering result is obtained, and suspected abnormal data are output;
and pushing the suspected abnormal data, detecting again, and determining whether the data is really abnormal data.
According to the further technical scheme, the acquired medical data are acquired from a medical insurance reimbursement related database and integrated after acquisition, and the medical diagnosis data of the hospital and the reimbursement data of the medical insurance bureau are integrated through the unique ID.
According to the further technical scheme, the integrated data are stored in a structured data set, data cleaning is conducted on the data set, feature extraction is conducted on the cleaned data, and features which are small in relation to judging whether the data are abnormal data or not are eliminated during feature extraction.
In a further technical scheme, the fuzzy C-means clustering model is a complex multidimensional function constructed through a data set, the output target value is suspected abnormal data judged through a fuzzy clustering algorithm, and the input is extracted characteristics.
In the further technical scheme, a fuzzy C-means clustering algorithm obtains a clustering center by minimizing a target function;
the target function is essentially the sum of Euclidean distances from each point to each class, the clustering process is the process of minimizing the target function, the error value of the target function is gradually reduced through repeated iterative operation, and when the target function is converged, the final clustering result can be obtained.
In the further technical scheme, the fuzzy C-means clustering algorithm is simply divided into four steps:
(1) establishing a standardized data matrix;
(2) establishing a fuzzy similar matrix and initializing a membership matrix;
(3) the algorithm starts iteration until the target function converges to a minimum value;
(4) and determining the class to which the data belongs according to the iteration result and the final membership matrix, and displaying the final clustering result.
According to the further technical scheme, a variance screening method is used for the cleaned hospitalization data set, a filtering threshold value is set to be 0, the features with small feature variance are filtered out, and the feature matrix dimensionality is reduced through a principal component analysis method.
In a second aspect, a system for detecting abnormal data of medical insurance reimbursement is disclosed, comprising:
a feature extraction module configured to: acquiring medical data, and performing data processing including data cleaning and feature extraction;
a suspected anomaly data output module configured to: based on the processed data, a fuzzy C-means clustering model is constructed, the medical data to be tested are clustered by using the model, a clustering result is obtained, and suspected abnormal data are output;
an anomaly data determination module configured to: and pushing the suspected abnormal data, detecting again, and determining whether the data is really abnormal data.
The above one or more technical solutions have the following beneficial effects:
according to the medical insurance medical service data processing method, the medical data of medical personnel are collected, data cleaning is carried out, medical insurance reimbursement abnormity detection is carried out based on a machine learning algorithm, the medical personnel with low scores are intelligently prompted to relevant workers for key detection and auditing, the calculation process is short, the calculation result is accurate, manual work can be greatly liberated, and the work efficiency is improved.
The medical personnel clustering method is based on the fuzzy C-means clustering algorithm, and is used for clustering the medical personnel, namely clustering is performed on the patients according to the medical information of the patients, so that the defects of a hard clustering method can be effectively overcome, the medical personnel can not be clustered hard, and the situations of misjudgment and excessive judgment in the detection process are avoided.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a system block diagram of an embodiment of the present disclosure;
fig. 2 is a flow chart of a method of an embodiment of the disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example one
The embodiment discloses a medical insurance reimbursement abnormity detection method based on a fuzzy C-means clustering algorithm, which comprises the following steps:
the method comprises the following steps: integrating the medical insurance reimbursement related database, and correspondingly associating the hospital and the medical insurance bureau data through the unique ID of the patient, such as an identity card, and passing the hospitalization diagnosis data of the hospital and the reimbursement data of the medical insurance bureau through the unique ID during integration;
step two: acquiring a structured data set; the system specifically comprises the patient name, the identification number, the sex, the social security organization number, the county and district number, the collection and payment organization number, the hospitalization date, the discharge date, the personnel type, the hospitalization category, the hospitalization mode, the disease name, the medicine purchasing times, the medicine name, the total amount, the medical insurance burden amount, the hospital burden amount, the patient burden amount, the overall payment amount, the partial self-burden amount and the like;
step three: performing data cleaning on the acquired data set;
step four: performing characteristic engineering on the data; the extracted features comprise the sex, the identification card number and the like which belong to the features of the patient, the feature extraction is carried out by a variance screening method and a principal component analysis method, and as the features of the structured data set are too many, the features with low correlation coefficient and little use for judging whether the patient cheats to take the fund can be eliminated by the two methods, thereby reducing the calculated amount and improving the accuracy;
step five: constructing a fuzzy C-means clustering model;
building a model is realized by programming languages such as Python and Java according to the fuzzy C-means clustering algorithm, so that a group of patient medical data is input, and the result of whether the patient medical data is suspected to be a person of a fraud medical insurance fund is output, wherein the model is a complex multidimensional function obtained by a current data set, and similar to a black box, the model can be understood that y is w1.x1+ w2.x2+. b, but the function is very complex, the parameters of the function are changed along with the function, y is a target value of the invention, the whole can be understood as a function, and what the invention needs to do is to optimize w and b, so that y is infinitely close to real y each time;
where x1, x2.. is the above feature, the output y is the suspected patient of fraud medical insurance fund judged by fuzzy clustering algorithm;
step six: performing abnormal point scoring;
the patient suspected of cheating the medical insurance fund and the hospitalizing data of the patient are obtained through the means, and at the moment, in the hospitalizing data of the patient, compared with the situation that which abnormal points are important and which abnormal points are not important, corresponding weights are given through investigation of workers in the early stage, the total score is calculated, the hospitalizing data and the score of the patient are pushed to the workers, manual identification is carried out, and the workload is reduced;
step seven: and intelligently prompting the staff.
In the second step, a structured medical data set is obtained through the relational database;
in the third step, data cleaning is carried out on the acquired hospitalizing data set, specifically comprising default value cleaning and format content cleaning, irrelevant data and repeated data in the original data set are deleted, and noise data are smoothed;
in the fourth step, a variance screening method is used for selecting proper features according to the cleaned hospitalization data set, and meanwhile, in order to avoid the situation that the calculated amount is increased greatly due to overlarge feature matrix, the feature matrix dimensionality is reduced through a Principal Component Analysis (PCA);
in the fifth step, a fuzzy C-means clustering model is constructed based on a fuzzy C-means clustering algorithm, and medical data processed in the third step are clustered;
the fuzzy C-means clustering model modeling process is realized through programming languages such as Python and Java, processed data are clustered in a Python environment based on a fuzzy C-means clustering algorithm, and abnormal medical insurance data cannot be normally clustered with the medical insurance data and are small in quantity and integrated.
With the continuous increase of the data volume, the output of the model is more and more accurate, namely, a group of patient medical data is input, the clustering is automatically carried out, and the result of whether the patient medical data is suspected to cheat the medical insurance fund is output.
The fuzzy C-means clustering algorithm obtains a clustering center by minimizing an objective function.
The objective function is essentially the sum of the euclidean distances (sum of squares of the errors) of the individual points to the individual classes.
The clustering process is a process of minimizing the target function, the error value of the target function is gradually reduced through repeated iterative operation, and when the target function is converged, a final clustering result can be obtained. Through the fuzzy C-means clustering algorithm, the patients can be clustered according to the hospitalization data, and the abnormal data of the medical insurance data can not be normally clustered with the medical insurance data, and are small in quantity and self-integrated.
The fuzzy C-means clustering algorithm is simply divided into four steps:
(1) establishing a standardized data matrix;
assume that a clustering object is U ═ x1,x2...xnEach object is the hospitalizing data of each patient, and each object is represented by m characteristics, namely, the hospitalizing hospitals of the patients, reimbursement amount, reimbursement categories and the like, and is represented as xi＝(xi1,xi2,...,xim)(i＝1,2,...,n)
The original data matrix is:
in practical problems, different data generally have different dimensions. In order to allow for the comparison of different dimensional quantities, it is often necessary to transform the data. However, since the obtained data is not always in the interval [0,1], the data normalization described here is to compress the data into the interval [0,1] and perform the data normalization by using the translational range transform in consideration of the operation speed and convenience.
(2) Establishing a fuzzy similar matrix and initializing a membership matrix;
establishing a fuzzy similarity matrix is also called calibration, namely for clustering objects U ═ x1,x2...xnAnd xi＝(xi1,xi2,...,xim) (i ═ 1, 2.. times, n), determining similarity coefficients according to a traditional clustering method, establishing a fuzzy similarity matrix, xiAnd xjDegree of similarity r ofij＝R(xi,xj) There are more than ten methods for determining the construction of fuzzy similarity matrix, and the maximum and minimum method is used:
(3) the algorithm starts iteration until the target function converges to a minimum value;
(4) and determining the class to which the data belongs according to the iteration result and the final membership matrix, and displaying the final clustering result.
In the sixth step, the outliers in the fifth step, namely the outliers, are scored;
and in the seventh step, intelligently prompting the lower-grade hospitalizing data in the sixth step to be pushed to relevant personnel for key detection and examination.
Specifically, referring to fig. 2, a specific process of the medical insurance reimbursement abnormality detection method based on the fuzzy C-means clustering algorithm of the present invention is as follows:
And step 204, receiving the visit reimbursement data cleaned by the data cleaning module 103, selecting proper features by using a variance screening method through the feature engineering module 104, and reducing feature matrix dimensions by using a Principal Component Analysis (PCA) method.
In step 206, outliers, i.e., outliers, in the clustering operation are scored by the outlier scoring module 106.
And step 207, the medical staff with low grade is sent through the intelligent prompting module 107.
Example two
It is an object of this embodiment to provide a computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method when executing the program.
EXAMPLE III
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
Example four
The device for detecting medical insurance reimbursement abnormity based on the fuzzy C-means clustering algorithm is shown in fig. 1 and comprises a hospitalizing information base module 101, a data acquisition module 102, a data cleaning module 103, a feature engineering module 104, a data modeling module 105, an abnormity scoring module 106 and an intelligent prompting module 107.
The medical information library module 101 is used for storing medical information, including medical insurance reimbursement amount and times;
a data acquisition module 102 for acquiring a structured medical data set;
the data cleaning module 103 is used for cleaning the data of the medical personnel in the medical data set, and removing invalid values, repeated values and the like;
the feature engineering module 104 is configured to use a variance screening method for the cleaned medical data set, set a filtering threshold to be 0, and filter out features with small variance of the features, where the small variance of one feature indicates that the sample has no difference on the feature, most of possible values in the feature are the same, and even the values of the entire feature are the same, and the feature has no effect on sample distinguishing, select a suitable feature, and reduce the feature matrix dimension by a Principal Component Analysis (PCA) in order to avoid an excessively large feature matrix, which may cause a drastic increase in the amount of calculation;
the data modeling module 105 is used for modeling the data set subjected to dimensionality reduction, constructing a fuzzy C-means clustering model based on a fuzzy C-means clustering algorithm, clustering the processed hospitalization data set and finding out outliers;
an anomaly scoring module 106 for performing scoring calculation for outliers, i.e. outliers;
and the intelligent prompting module 107 is used for pushing medical personnel with abnormal scores to relevant staff to perform key detection and examination.
By applying the artificial intelligence algorithm, the calculation process is short, the calculation result is accurate, the manpower can be greatly liberated, and the working efficiency of personnel is improved; meanwhile, compared with a general hard clustering algorithm, the fuzzy C-Means-based clustering algorithm has a more flexible clustering result and better applicability to medical insurance reimbursement abnormity detection.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present disclosure.
Those skilled in the art will appreciate that the modules or steps of the present disclosure described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code executable by computing means, whereby the modules or steps may be stored in memory means for execution by the computing means, or separately fabricated into individual integrated circuit modules, or multiple modules or steps thereof may be fabricated into a single integrated circuit module. The present disclosure is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. The method for detecting the abnormal data of medical insurance reimbursement is characterized by comprising the following steps:
acquiring medical data, and performing data processing including data cleaning and feature extraction;
based on the processed data, a fuzzy C-means clustering model is constructed, the medical data to be tested are clustered by using the model, a clustering result is obtained, and suspected abnormal data are output;
and pushing the suspected abnormal data, detecting again, and determining whether the data is really abnormal data.
2. The method as claimed in claim 1, wherein the acquired medical data is acquired from a medical insurance reimbursement related database, and the acquired medical data is integrated, so as to integrate the medical diagnosis data of the hospital and the reimbursement data of the medical insurance bureau via a unique ID card.
3. The method as claimed in claim 1, wherein the integrated data is stored in a structured data set, the data set is cleaned, the cleaned data is subjected to feature extraction, and features with small association to determine whether the data is abnormal data are removed during feature extraction.
4. The method of claim 1, wherein the fuzzy C-means clustering model is a complex multidimensional function constructed by a data set, the output target value is suspected abnormal data judged by a fuzzy clustering algorithm, and the input is the extracted feature.
5. The method of claim 1, wherein the fuzzy C-means clustering algorithm minimizes an objective function to obtain a clustering center;
the target function is essentially the sum of Euclidean distances from each point to each class, the clustering process is the process of minimizing the target function, the error value of the target function is gradually reduced through repeated iterative operation, and when the target function is converged, the final clustering result can be obtained.
6. The method for detecting medical insurance reimbursement abnormal data according to claim 1, wherein the fuzzy C-means clustering algorithm is simply divided into four steps:
(1) establishing a standardized data matrix;
(2) establishing a fuzzy similar matrix and initializing a membership matrix;
(3) the algorithm starts iteration until the target function converges to a minimum value;
(4) and determining the class to which the data belongs according to the iteration result and the final membership matrix, and displaying the final clustering result.
7. The method as claimed in claim 1, wherein the variance screening is used to set the filtering threshold value to 0 and filter out the features with smaller variance, and the feature matrix dimension is reduced by principal component analysis.
8. Medical insurance reimbursement abnormal data detection system, characterized by includes:
a feature extraction module configured to: acquiring medical data, and performing data processing including data cleaning and feature extraction;
a suspected anomaly data output module configured to: based on the processed data, a fuzzy C-means clustering model is constructed, the medical data to be tested are clustered by using the model, a clustering result is obtained, and suspected abnormal data are output;
an anomaly data determination module configured to: and pushing the suspected abnormal data, detecting again, and determining whether the data is really abnormal data.
9. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of performing the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110739794.3A CN113436027B (en) | 2021-06-30 | 2021-06-30 | Medical insurance reimbursement abnormal data detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110739794.3A CN113436027B (en) | 2021-06-30 | 2021-06-30 | Medical insurance reimbursement abnormal data detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113436027A true CN113436027A (en) | 2021-09-24 |
| CN113436027B CN113436027B (en) | 2022-11-22 |
Family
ID=77758281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110739794.3A Active CN113436027B (en) | 2021-06-30 | 2021-06-30 | Medical insurance reimbursement abnormal data detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113436027B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957421A (en) * | 2023-09-20 | 2023-10-27 | 山东济宁运河煤矿有限责任公司 | Washing and selecting production intelligent monitoring system based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170102978A1 (en) * | 2015-10-07 | 2017-04-13 | Business Objects Software Ltd. | Detecting anomalies in an internet of things network |
| CN108921710A (en) * | 2018-06-08 | 2018-11-30 | 东莞迪赛软件技术有限公司 | The method and system of medical insurance abnormality detection |
| CN109087711A (en) * | 2018-06-28 | 2018-12-25 | 郑州大学第附属医院 | Medical big data method for digging and system |
| CN109636645A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN110852374A (en) * | 2019-11-08 | 2020-02-28 | 腾讯云计算（北京）有限责任公司 | Data detection method and device, electronic equipment and storage medium |
| CN112560921A (en) * | 2020-12-10 | 2021-03-26 | 百维金科(上海)信息科技有限公司 | Internet financial platform application fraud detection method based on fuzzy C-mean |
| CN112632609A (en) * | 2020-12-23 | 2021-04-09 | 深圳云天励飞技术股份有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium |
-
2021
- 2021-06-30 CN CN202110739794.3A patent/CN113436027B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170102978A1 (en) * | 2015-10-07 | 2017-04-13 | Business Objects Software Ltd. | Detecting anomalies in an internet of things network |
| CN108921710A (en) * | 2018-06-08 | 2018-11-30 | 东莞迪赛软件技术有限公司 | The method and system of medical insurance abnormality detection |
| CN109087711A (en) * | 2018-06-28 | 2018-12-25 | 郑州大学第附属医院 | Medical big data method for digging and system |
| CN109636645A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN110852374A (en) * | 2019-11-08 | 2020-02-28 | 腾讯云计算（北京）有限责任公司 | Data detection method and device, electronic equipment and storage medium |
| CN112560921A (en) * | 2020-12-10 | 2021-03-26 | 百维金科(上海)信息科技有限公司 | Internet financial platform application fraud detection method based on fuzzy C-mean |
| CN112632609A (en) * | 2020-12-23 | 2021-04-09 | 深圳云天励飞技术股份有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957421A (en) * | 2023-09-20 | 2023-10-27 | 山东济宁运河煤矿有限责任公司 | Washing and selecting production intelligent monitoring system based on artificial intelligence |
| CN116957421B (en) * | 2023-09-20 | 2024-01-05 | 山东济宁运河煤矿有限责任公司 | Washing and selecting production intelligent monitoring system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113436027B (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785976B (en) | Gout disease stage prediction system based on Soft-Voting | |
| CN107731269B (en) | Disease coding method and system based on original diagnosis data and medical record file data | |
| US7386506B2 (en) | Fraud score calculating program, method of calculating fraud score, and fraud score calculating system for credit cards | |
| CN112365987A (en) | Diagnostic data anomaly detection method and device, computer equipment and storage medium | |
| Karthikeyan et al. | Analysis of classification algorithms applied to hepatitis patients | |
| CN109378066A (en) | A kind of control method and control device for realizing disease forecasting based on feature vector | |
| CN112950614B (en) | Breast cancer pathological image classification method based on multi-scale cavity convolution | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| CN111785384A (en) | Abnormal data identification method based on artificial intelligence and related equipment | |
| CN113392894A (en) | Cluster analysis method and system for multi-group mathematical data | |
| CN111612038A (en) | Abnormal user detection method and device, storage medium and electronic equipment | |
| CN117078026B (en) | Wind control index management method and system based on data blood margin | |
| WO2021120587A1 (en) | Method and apparatus for retina classification based on oct, computer device, and storage medium | |
| Ali et al. | A novel approach for best parameters selection and feature engineering to analyze and detect diabetes: Machine learning insights | |
| CN113436027B (en) | Medical insurance reimbursement abnormal data detection method and system | |
| CN114519705A (en) | Ultrasonic standard data processing method and system for medical selection and identification | |
| CN116013511B (en) | Intelligent recommendation method and system for diabetes intervention based on knowledge graph | |
| CN117352164A (en) | Multi-mode tumor detection and diagnosis platform based on artificial intelligence and processing method thereof | |
| US20030191732A1 (en) | Online learning method in a decision system | |
| CN115862897A (en) | Syndrome monitoring method and system based on clinical data | |
| CN109635112A (en) | Abnormal dialysis data screening method, apparatus, equipment and storage medium | |
| CN113838018B (en) | Cnn-former-based liver fibrosis lesion detection model training method and system | |
| CN114862597A (en) | Health insurance claim settlement risk prediction method and system based on medical big data | |
| CN114999628A (en) | Method for searching significant characteristics of degenerative knee osteoarthritis by machine learning | |
| CN114550930A (en) | Disease prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |