CN110781222A - Abnormal medical insurance application detection method and device, computer equipment and storage medium - Google Patents
Abnormal medical insurance application detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110781222A CN110781222A CN201910971925.3A CN201910971925A CN110781222A CN 110781222 A CN110781222 A CN 110781222A CN 201910971925 A CN201910971925 A CN 201910971925A CN 110781222 A CN110781222 A CN 110781222A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- medicine
- medication
- drug
- medicines
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 315
- 238000001514 detection method Methods 0.000 title claims description 23
- 239000003814 drug Substances 0.000 claims abstract description 790
- 229940079593 drug Drugs 0.000 claims abstract description 485
- 241000208340 Araliaceae Species 0.000 claims abstract description 71
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims abstract description 71
- 235000003140 Panax quinquefolius Nutrition 0.000 claims abstract description 71
- 235000008434 ginseng Nutrition 0.000 claims abstract description 71
- 201000010099 disease Diseases 0.000 claims abstract description 49
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000001647 drug administration Methods 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 23
- 238000010586 diagram Methods 0.000 claims description 17
- 238000013075 data extraction Methods 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002547 anomalous effect Effects 0.000 claims description 4
- 229940126534 drug product Drugs 0.000 claims 2
- 239000000825 pharmaceutical preparation Substances 0.000 claims 2
- 238000012544 monitoring process Methods 0.000 abstract 1
- 239000000284 extract Substances 0.000 description 4
- 241000411851 herbal medicine Species 0.000 description 3
- 238000000968 medical method and process Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
Abstract
The application relates to the field of monitoring models of intelligent decision-making, in particular to a method and a device for detecting abnormal medical insurance application, a computer device and a storage medium. The method comprises the following steps: extracting a medicine use record of the medical insurance application to be claim for settlement; and inputting the medicine use type data into a preset isolated forest model, and acquiring the abnormal medicine use weight values of various medicines in each medicine prescription to obtain the abnormal medicine use weight values of each medicine prescription. Counting the total cost of the primary medicines of the ginseng and insurance people under each disease category, and judging whether the cost is abnormal medicines or not by using a box chart algorithm; and when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application. The medical insurance application is detected from two angles of whether the medicine use in the medical insurance application submitted by the insurer is abnormal or not and whether the medicine cost is abnormal or not, whether the medical insurance application violates the rules or regulations or not is comprehensively judged, and the accuracy of detecting the medication violation of the medical insurance outpatient service is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for detecting an abnormal medical insurance application, a computer device, and a storage medium.
Background
At present, whether outpatient medication violation occurs in medical insurance, the medication deviation in the outpatient medication process is mostly detected through deviation detection, abnormal data in the medication deviation are extracted, however, the deviation detection is not sensitive to small-scale violation in a medicine prescription of outpatient medication, and the accuracy of the abnormality detection process cannot be ensured.
Disclosure of Invention
In view of the above, it is necessary to provide an abnormal medical insurance application detection method, apparatus, computer device and storage medium capable of accurately detecting whether the outpatient medication process of the medical insurance is violated, in order to solve the problem that the existing deviation detection method cannot ensure the accuracy of the abnormal medication detection of the outpatient service of the medical insurance.
A method of anomalous medical insurance application detection, the method comprising:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
acquiring a visit information list, counting the total cost of the ginseng and insurance individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and insurance individual medicines is the cost of abnormal medicines or not by using a boxed graph algorithm;
and when the abnormal drug administration weight value of the drug prescription is in an abnormal area and the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
In one embodiment, the extracting medication type data corresponding to each drug prescription from the drug usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various drugs in each drug prescription, and obtaining the medication abnormal weight values of each drug prescription according to the medication abnormal weight values of various drugs in each drug prescription includes:
running the medication type data corresponding to each medicine prescription on the isolated trees corresponding to each medicine in the preset isolated forest model, and recording the path length of the medication type data in the running process;
determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths;
and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
In one embodiment, the obtaining, according to the medication abnormality weight value corresponding to each drug in each drug prescription, a medication abnormality weight value corresponding to each drug prescription includes:
when the medicine prescriptions contain preset abnormal medicine combinations, acquiring abnormal weighting coefficients corresponding to the preset abnormal medicine combinations, carrying out weighting calculation on the medication abnormal weight values of the medicines in the preset abnormal medicine combinations according to the abnormal weighting coefficients to obtain weighted abnormal weight values, and taking the average of the weighted abnormal weight values and medication abnormal weight values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weight values corresponding to the current medicine prescriptions;
and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
In one embodiment, the extracting medication type data corresponding to each drug prescription from the drug usage record, inputting the medication type data into a preset isolated forest model, obtaining abnormal medication weight values of each drug in each drug prescription, and before obtaining the abnormal medication weight values of each drug prescription according to the abnormal medication weight values of each drug in each drug prescription, further includes:
constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription containing the current medicine in the historical record;
and constructing a preset isolated forest model according to the isolated tree.
In one embodiment, the obtaining a visit information list, counting total costs of the insured single-time drugs under each disease category according to the visit information list, and determining whether the total costs of the insured single-time drugs are abnormal drug costs by using a boxplot algorithm includes:
acquiring a medical insurance information statement of a patient to be protected according to the application of the medical insurance of the claim to be settled;
according to the visit information list of the ginseng insurance people, the total cost of single medicines of the ginseng insurance people under each disease category is counted;
acquiring single medicine expense history records of insurers corresponding to various diseases, determining a box diagram corresponding to the total expense of the ginseng and insured single medicines according to the single medicine expense history records of the insurers corresponding to various diseases, and setting the total expense range of the ginseng and insured single medicines corresponding to the number of edges larger than the upper edge number of the box diagram as the expense of abnormal medicines;
and acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
In one embodiment, before determining that the application for medical insurance to be settled is an abnormal application when the abnormal drug weight value of the drug prescription is in the abnormal area or the total cost of the single drug is the abnormal drug cost, the method further includes:
acquiring abnormal drug weight values of the preset isolated forest model to the drug prescriptions in the historical records;
acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescriptions in each historical record;
and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
An anomalous medical insurance application detection apparatus, said apparatus comprising:
the application receiving module is used for acquiring the medical insurance application to be claim settled and extracting the medicine use record of the medical insurance application to be claim settled;
the first data extraction module is used for extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, acquiring medication abnormal weight values of various medicines in each medicine prescription, and acquiring the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
the second data extraction module is used for acquiring a visit information detailed table, counting the total cost of the ginseng and insurance individual single-time medicines under each disease category according to the visit information detailed table, and judging whether the total cost of the ginseng and insurance individual single-time medicines is the cost of abnormal medicines or not by using a box chart algorithm;
and the violation judging module is used for judging that the medical insurance application to be claim settled is an abnormal application when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug expense.
In one embodiment, the first data extraction module is specifically configured to:
running the medication type data corresponding to each medicine prescription on the isolated trees corresponding to each medicine in the preset isolated forest model, and recording the path length of the medication type data in the running process;
determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths;
and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
counting the medication type data corresponding to each medicine prescription according to the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription.
Acquiring a visit information list, counting the total cost of the ginseng and insurance individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and insurance individual medicines is the cost of abnormal medicines or not by using a boxed graph algorithm;
and when the abnormal drug administration weight value of the drug prescription is in an abnormal area or the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
counting the medication type data corresponding to each medicine prescription according to the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription.
Acquiring a visit information list, counting the total cost of the ginseng and insurance individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and insurance individual medicines is the cost of abnormal medicines or not by using a boxed graph algorithm;
and when the abnormal drug administration weight value of the drug prescription is in an abnormal area or the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
According to the abnormal medical insurance application detection method, the abnormal medical insurance application detection device, the computer equipment and the storage medium, the medical insurance application to be claim is obtained, and the medicine use record of the medical insurance application to be claim is extracted; counting the medication type data corresponding to each medicine prescription according to the medicine use record, inputting the medication type data into a preset isolated forest model, acquiring medication abnormal weight values of various medicines in each medicine prescription, and acquiring the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription. Acquiring a visit information list, counting the total cost of the ginseng and protected individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and protected individual medicines is the cost of abnormal medicines or not by using a boxchart algorithm; and when the abnormal drug administration weight value of the drug prescription is in an abnormal area or the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application. The medical insurance application is detected from two angles of whether the medicine use in the medical insurance application submitted by the insurer is abnormal or not and whether the medicine cost is abnormal or not, whether the medical insurance application violates the rules or regulations or not is comprehensively judged, and the accuracy of detecting the medication violation of the medical insurance outpatient service is improved.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of an application environment of a method for detecting an abnormal medical insurance application;
FIG. 2 is a schematic flow chart illustrating a method for detecting an abnormal medical insurance application in one embodiment;
FIG. 3 is a flow diagram illustrating sub-steps of step S400 of FIG. 2 according to one embodiment;
FIG. 4 is a flow diagram illustrating sub-steps of step S600 of FIG. 2 according to one embodiment;
FIG. 5 is a block diagram showing the structure of an apparatus for detecting an abnormal medical insurance application in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The abnormal medical insurance application detection method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 can submit a medical insurance application to be claim-settled to the server 104, the server 104 verifies the medical insurance application and judges whether the medical insurance application is abnormal, the server 104 obtains the medical insurance application to be claim-settled and extracts a medicine use record of the medical insurance application to be claim-settled; extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription. Acquiring a visit information list, counting the total cost of the ginseng and protected individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and protected individual medicines is the cost of abnormal medicines or not by using a boxchart algorithm; and when the abnormal medicine taking weight value of the medicine prescription belongs to an abnormal area or whether the total cost of the single medicine is the time spent on the abnormal medicine or not, judging that the application of the medical insurance to be settled is an abnormal violation application. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a method for detecting an abnormal medical insurance application is provided, which is described by taking the method applied to the server side in fig. 1 as an example, and includes the following steps:
s200, acquiring the medical insurance application to be claim settled, and extracting the medicine use record of the medical insurance application to be claim settled.
The application of the medical insurance to be settled refers to an application submitted to the server side by the terminal according to the medical information of the paramedics of the medical insurance. The application for medical insurance to be settled may specifically include information of medical insurance bought by the insurer, a record of drug usage and drug cost information of the insurer during medical treatment, and the like, and the medication information specifically includes various outpatient prescriptions in the course of medication and the kind of medication in the prescription, and the like. The server obtains the medical insurance application to be claim settled submitted by the terminal, extracts the drug use record of the insured person from the medical insurance application, and judges whether the medication of the medical insurance application of the insured person is illegal or not according to the record.
Specifically, the medical insurance application to be claimed, provided by the terminal to the server side, may include a plurality of record forms, including a visit information detail form of the insured person, the form including the drug usage record of the insured person, and the server may directly extract the drug usage record in the medical insurance application to be claimed.
S400, extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription.
Each medicine prescription refers to a medicine prescription used by the ginseng insurance people in the outpatient service medication process, and the medication type data specifically refers to the types of medicines contained in the prescription. In one embodiment, when the drug prescription is a Chinese herbal medicine prescription, the medication type data is the number of Chinese herbal medicines in the Chinese herbal medicine prescription. The preset isolated forest model is an anomaly detection model constructed by an isolated forest algorithm and used for judging whether the medication type corresponding to each medicine in each input medicine prescription is abnormal data, namely, the medication anomaly weight value is used, and the medication anomaly weight value corresponding to the medicine prescription used in the medical process of the insured person is obtained by combining the medication anomaly weight value corresponding to each medicine in the medicine prescription.
S600, obtaining a visit information list, counting the total cost of the ginseng and insurance person single-time medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and insurance person single-time medicines is abnormal medicine cost or not by using a box chart algorithm.
The medical insurance application to be settled comprises a visit information list of the insured person, the visit information list comprises all medical expense information recorded in the medical process of the insured person, and the total cost of single medicines of the insured person in a single disease can be determined through the medical expense information. The total cost of medicines for a patient is the total cost of all medicines used by the patient under a single disease in the current medical insurance process. The box chart is called box whisker chart, box chart or box chart, and is a statistical chart for displaying a group of data dispersion condition data. The shape of the box is called. The method is mainly used for reflecting the distribution characteristics of the original data and can also be used for comparing a plurality of groups of data distribution characteristics. The box line graph drawing method comprises the following steps: firstly, finding out the maximum value, the minimum value, the median and two quartiles of a group of data; then, connecting the two quartiles to draw a box; the maximum and minimum values are then connected to the boxes with the median in the middle of the boxes. The box-type graph can be drawn according to the total cost of the single medicines of the current patient in the historical records within the preset time, and then whether the total cost of the single medicines of the current patient in the currently input medical insurance application for claim settlement belongs to abnormal data or not can be judged according to the box-type graph.
And S800, when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug expense, judging that the medical insurance application to be claim is an abnormal application.
After the abnormal medication weight value of the medicine prescription is obtained through abnormal detection, whether the abnormal medication weight value of the medicine prescription is outside a preset normal range or not can be judged, namely, whether the abnormal medication weight value of the medicine prescription is in an abnormal area or not can be judged, and when the condition that the medicine prescription is in the abnormal area and whether the total single-time medicine cost of a participant is abnormal medicine cost or not exists in the application for medical insurance to be claimed, the application for medical insurance to be claimed can be judged to be an abnormal violation application. The abnormal area of the medication abnormal weight value can be determined by summarizing the distribution of the medication abnormal weight value in the historical record by using a preset isolated forest model.
According to the abnormal medical insurance application detection method, the medical insurance application to be claim is obtained, and the medicine use record of the medical insurance application to be claim is extracted; counting the medication type data corresponding to each medicine prescription according to the medicine use record, inputting the medication type data into a preset isolated forest model, acquiring medication abnormal weight values of various medicines in each medicine prescription, and acquiring the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription. Acquiring a visit information list, counting the total cost of the ginseng and protected individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and protected individual medicines is the cost of abnormal medicines or not by using a boxchart algorithm; and when the abnormal drug administration weight value of the drug prescription is in an abnormal area or the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application. The medical insurance application is detected from two angles of whether the medicine use in the medical insurance application submitted by the insurer is abnormal or not and whether the medicine cost is abnormal or not, whether the medical insurance application violates the rules or regulations or not is comprehensively judged, and the accuracy of detecting the medication violation of the medical insurance outpatient service is improved.
As shown in fig. 3, in one embodiment, step S400 includes:
and S410, running the medication type data corresponding to each medicine prescription on an isolated tree corresponding to each medicine in a preset isolated forest model, and recording the path length of the medication type data in the running process.
And S430, determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths.
S450, acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
The isolated forest model is a model established based on an isolated forest algorithm, and the isolated forest algorithm is generally used for mining abnormal data or outlier mining, namely, finding out data which is not in accordance with the rules of other data in a large pile of data. Specifically, the number of medicines in the prescription of each medicine used in statistics can be extracted from the detail table by extracting the visit record detail table of the insurer in the application for claims to be settled.
The process of obtaining the abnormal medication weight value of a single drug in the drug prescription specifically includes that the medication category data corresponding to the drug prescription is downward along the corresponding branch in the isolated tree in the soliton until reaching a leaf node, the length of the path through which the data passes is recorded, and the abnormal medication weight value corresponding to the drug in the current drug prescription is determined according to the length of the path. And then determining the medication abnormity weight values corresponding to the medicine prescription according to the medication abnormity weight values corresponding to all medicines in the current medicine prescription. The abnormal medication weight value corresponding to a single medicine in the medicine prescription is obtained through the preset isolated forest model, and then the abnormal medication weight value of the whole medicine prescription is judged in a combined mode, so that the judgment on whether the medication number in the medicine prescription is abnormal or not can be effectively improved.
In one embodiment, obtaining the medication abnormality weight value corresponding to each medicine prescription according to the medication abnormality weight value corresponding to each medicine in each medicine prescription includes:
when the medicine prescriptions contain the preset abnormal medicine combination, acquiring an abnormal weighting coefficient corresponding to the preset abnormal medicine combination, carrying out weighting calculation on the medication abnormal weighting values of the medicines in the preset abnormal medicine combination according to the abnormal weighting coefficient to obtain a weighted abnormal weighting value, and taking the average of the weighted abnormal weighting values and the medication abnormal weighting values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weighting value corresponding to the current medicine prescription;
and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
In particular, sometimes a plurality of medicines cannot appear simultaneously, an obtaining way of abnormal scores can be added by considering the situation, specific medicine combinations can also be detected, when the combinations appear in the medicine prescription, abnormal weight values of the medicines in the combinations can be combined and processed, abnormal scores corresponding to the scores of the medicine combinations in a single prescription are obtained through a preset isolated forest model, the score of the medicine A is 10, the score of the medicine B is 20, and the scores of the medicine A and the medicine B are combined to be 50 when the medicine A and the medicine B appear in the same prescription. The medication abnormity weight values of the medicines in the medicine prescription are weighted and averaged, so that the medication abnormity weight value corresponding to the current medicine prescription can be effectively obtained.
In one embodiment, S400 further includes, before:
constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription of the current medicine in the historical record;
and constructing a preset isolated forest model according to the isolated tree.
The unmarked training feature set refers to a feature set used for training an isolated forest model, and the training feature set consists of medicine prescriptions in historical records. The isolated forest model is composed of a plurality of isolated trees, each isolated tree in a medicine prescription is established based on a unmarked training feature set, and the isolated forest model is composed of the plurality of isolated trees. The unmarked training feature set comprises a medicine prescription, the medicine prescription specifically comprises medicines in the medicine prescription and medicine type data of the medicine prescription, a certain medicine can be randomly selected from the medicine prescription for training to establish an isolated tree, and then a plurality of isolated trees containing all kinds of medicines are generated based on a large amount of unmarked data training to form an isolated forest. The process of constructing the corresponding isolated tree of each medicine according to the unmarked training feature set specifically comprises the following steps: randomly selecting a value V between the maximum value and the minimum value of the range of the prescription flavor number of the medicine, dividing the number larger than the value on the right side and the number smaller than the value on the left side, then repeating the above operations on the data on the left side and the right side respectively, and constructing an isolated tree in a recursive manner until only one record or the height of the tree reaches a limit log2, and stopping the operation. A preset isolated forest model is constructed through medicine prescription data in historical data, the preset isolated forest model can acquire medication abnormity weight values corresponding to medicines in a medicine prescription, and whether the medicine prescription is abnormal or not can be accurately judged by combining the medication abnormity weight values of all the medicines in the medicine prescription.
As shown in fig. 4, in one embodiment, S600 includes:
s610, acquiring a medical information statement of the patient to be protected according to the application of the medical insurance of the claim to be settled.
And S630, counting the total cost of the single-time medicines of the ginseng and insured people under each disease category according to the detailed information list of the diagnosis information of the ginseng and insured people.
S650, acquiring the single medicine expense history records of the insured person corresponding to each disease type, determining the box chart corresponding to the total expense of the single medicines of the insured person according to the single medicine expense history records of the insured person corresponding to each disease type, and setting the total expense range of the single medicines of the insured person corresponding to the number of edges larger than the upper edge of the box chart as the expense of the abnormal medicines.
And S670, acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
The ginseng and insurance patient visit information list specifically comprises all the drug costs of the ginseng and insurance in the medical process, and the server can classify the costs according to the ginseng and insurance patient visit information list and classify all the drug costs under a single disease into one class. Before the server judges the abnormal cost of the single-disease medicine, the maximum value, the minimum value, the median and two quartiles of the total cost of the medicines can be obtained according to the total cost of the medicines under all the single-disease medicines in the historical record; then, connecting the two quartiles to draw a box; and connecting the maximum value and the minimum value with the boxes, wherein the median is positioned in the middle of the boxes, and obtaining a box chart corresponding to each single disease charge. And setting the total expense range of the single-time medicines of the insured person corresponding to the number of edges on the boxmap as the expense of the abnormal medicines. Meanwhile, the expense range corresponding to the upper quartile to the upper marginal number can be determined as the expense of the suspicious drug. The server can firstly obtain the total expense of the single-time medicines of the insured person under each disease category corresponding to the input medical insurance application to be claim, and judge whether the total expense of the single-time medicines of each insured person in the currently input medical insurance application to be claim belongs to abnormal data or not through box-type graphs corresponding to each disease category. Whether the total cost of the single medicine under the single disease category of the insured person is abnormal or not can be effectively and accurately judged through the box-type graph.
In one embodiment, S800 further includes, before:
acquiring abnormal drug weight values of the preset isolated forest model to the drug prescriptions in the historical records;
acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescription in each historical record;
and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
The medicine prescription score distribution of the middle training data is obtained by scoring each training data prescription, and the prescription with the score outside the (mu-3 sigma, mu +3 sigma) interval of the medicine prescription type score is judged to be the prescription with abnormal medicine type by using a 3 delta-rule. The abnormal region of the medication type score of the medication prescription can be accurately estimated by the 3 delta-rule of normal distribution. And then accurately judging whether the medicine prescription is an abnormal prescription or not based on the abnormal area of the medicine abnormal weight value.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided an abnormal medical insurance application detection apparatus, including:
the application receiving module 200 is configured to obtain a medical insurance application to be claimed, and extract a drug usage record of the medical insurance application to be claimed;
the first data extraction module 400 is configured to extract medication category data corresponding to each drug prescription from the drug usage record, input the medication category data into a preset isolated forest model, obtain medication abnormal weight values of various drugs in each drug prescription, and obtain medication abnormal weight values of each drug prescription according to the medication abnormal weight values of various drugs in each drug prescription.
The second data extraction module 600 is configured to obtain the visit information detail table, count total costs of the ginseng insurance person single-time drugs under each disease category according to the visit information detail table, and determine whether the total costs of the ginseng insurance person single-time drugs are abnormal drug costs by using a boxed graph algorithm.
And the violation determining module 800 is configured to determine that the medical insurance application to be claimed is an abnormal application when the abnormal medication weight value of the medicine prescription is in the abnormal area and the total cost of the single medicine is the abnormal medicine cost.
In one embodiment, the first data extraction module 400 is specifically configured to: running the medication type data corresponding to each medicine prescription on an isolated tree corresponding to each medicine in a preset isolated forest model, and recording the path length of the medication type data in the running process; determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths; and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
In one embodiment, the first data extraction module 400 is further configured to: when the medicine prescriptions contain the preset abnormal medicine combination, acquiring an abnormal weighting coefficient corresponding to the preset abnormal medicine combination, carrying out weighting calculation on the medication abnormal weighting values of the medicines in the preset abnormal medicine combination according to the abnormal weighting coefficient to obtain a weighted abnormal weighting value, and taking the average of the weighted abnormal weighting values and the medication abnormal weighting values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weighting value corresponding to the current medicine prescription; and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
In one embodiment, the system further comprises a model building module for: constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription of the current medicine in the historical record; and constructing a preset isolated forest model according to the isolated tree.
In one embodiment, the second data extraction module 600 is specifically configured to: acquiring a medical insurance information statement of a patient to be protected according to the application of the medical insurance of the claim to be settled; according to the visit information list of the ginseng insurance people, the total cost of single medicines of the ginseng insurance people under each disease category is counted; acquiring single medicine expense history records of insurers corresponding to various diseases, determining a box diagram corresponding to the total expense of the ginseng and insured single medicines according to the single medicine expense history records of the insurers corresponding to various diseases, and setting the total expense range of the ginseng and insured single medicines corresponding to the number of edges larger than the upper edge number of the box diagram as the expense of abnormal medicines; and acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
In one embodiment, the system further comprises an abnormal region identification module, a medicine taking abnormal weight value of each historical record medicine prescription is obtained by a preset isolated forest model; acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescription in each historical record; and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
For specific limitations of the abnormal medical insurance application detection device, reference may be made to the above limitations of the abnormal medical insurance application detection method, which are not described herein again. All modules in the abnormal medical insurance application detection device can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing isolated forest models and box plot related data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an abnormal medical insurance application detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
extracting the medication type data corresponding to each medicine prescription from the medicine use record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
acquiring a visit information list, counting the total cost of the ginseng and protected individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and protected individual medicines is the cost of abnormal medicines or not by using a boxchart algorithm;
and when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
In one embodiment, the processor, when executing the computer program, further performs the steps of: running the medication type data corresponding to each medicine prescription on an isolated tree corresponding to each medicine in a preset isolated forest model, and recording the path length of the medication type data in the running process; determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths; and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the medicine prescriptions contain the preset abnormal medicine combination, acquiring an abnormal weighting coefficient corresponding to the preset abnormal medicine combination, carrying out weighting calculation on the medication abnormal weighting values of the medicines in the preset abnormal medicine combination according to the abnormal weighting coefficient to obtain a weighted abnormal weighting value, and taking the average of the weighted abnormal weighting values and the medication abnormal weighting values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weighting value corresponding to the current medicine prescription; and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
In one embodiment, the processor, when executing the computer program, further performs the steps of: constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription of the current medicine in the historical record; and constructing a preset isolated forest model according to the isolated tree.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a medical insurance information statement of a patient to be protected according to the application of the medical insurance of the claim to be settled; according to the visit information list of the ginseng insurance people, the total cost of single medicines of the ginseng insurance people under each disease category is counted; acquiring single medicine expense history records of insurers corresponding to various diseases, determining a box diagram corresponding to the total expense of the ginseng and insured single medicines according to the single medicine expense history records of the insurers corresponding to various diseases, and setting the total expense range of the ginseng and insured single medicines corresponding to the number of edges larger than the upper edge number of the box diagram as the expense of abnormal medicines; and acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring abnormal drug weight values of the preset isolated forest model to the drug prescriptions in the historical records; acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescription in each historical record; and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
extracting the medication type data corresponding to each medicine prescription from the medicine use record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
acquiring a visit information list, counting the total cost of the ginseng and protected individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and protected individual medicines is the cost of abnormal medicines or not by using a boxchart algorithm;
and when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
In one embodiment, the computer program when executed by the processor further performs the steps of: running the medication type data corresponding to each medicine prescription on an isolated tree corresponding to each medicine in a preset isolated forest model, and recording the path length of the medication type data in the running process; determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths; and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the medicine prescriptions contain the preset abnormal medicine combination, acquiring an abnormal weighting coefficient corresponding to the preset abnormal medicine combination, carrying out weighting calculation on the medication abnormal weighting values of the medicines in the preset abnormal medicine combination according to the abnormal weighting coefficient to obtain a weighted abnormal weighting value, and taking the average of the weighted abnormal weighting values and the medication abnormal weighting values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weighting value corresponding to the current medicine prescription; and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
In one embodiment, the computer program when executed by the processor further performs the steps of: constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription of the current medicine in the historical record; and constructing a preset isolated forest model according to the isolated tree.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a medical insurance information statement of a patient to be protected according to the application of the medical insurance of the claim to be settled; according to the visit information list of the ginseng insurance people, the total cost of single medicines of the ginseng insurance people under each disease category is counted; acquiring single medicine expense history records of insurers corresponding to various diseases, determining a box diagram corresponding to the total expense of the ginseng and insured single medicines according to the single medicine expense history records of the insurers corresponding to various diseases, and setting the total expense range of the ginseng and insured single medicines corresponding to the number of edges larger than the upper edge number of the box diagram as the expense of abnormal medicines; and acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring abnormal drug weight values of the preset isolated forest model to the drug prescriptions in the historical records; acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescription in each historical record; and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of anomalous medical insurance application detection, the method comprising:
acquiring a medical insurance application to be claim settled, and extracting a medicine use record of the medical insurance application to be claim settled;
extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, obtaining medication abnormal weight values of various medicines in each medicine prescription, and obtaining the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
acquiring a visit information list, counting the total cost of the ginseng and insurance individual medicines under each disease category according to the visit information list, and judging whether the total cost of the ginseng and insurance individual medicines is the cost of abnormal medicines or not by using a boxed graph algorithm;
and when the abnormal drug administration weight value of the drug prescription is in an abnormal area and the total cost of the single drug is the abnormal drug cost, judging that the medical insurance application to be claim is an abnormal application.
2. The method of claim 1, wherein the extracting medication category data corresponding to each drug prescription from the drug usage record, inputting the medication category data into a preset isolated forest model, obtaining medication abnormal weight values of various drugs in each drug prescription, and obtaining the medication abnormal weight values of each drug prescription according to the medication abnormal weight values of various drugs in each drug prescription comprises:
running the medication type data corresponding to each medicine prescription on the isolated trees corresponding to each medicine in the preset isolated forest model, and recording the path length of the medication type data in the running process;
determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths;
and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
3. The method of claim 2, wherein the obtaining of the medication abnormality weight value corresponding to each drug prescription according to the medication abnormality weight value corresponding to each drug in each drug prescription comprises:
when the medicine prescriptions contain preset abnormal medicine combinations, acquiring abnormal weighting coefficients corresponding to the preset abnormal medicine combinations, carrying out weighting calculation on the medication abnormal weight values of the medicines in the preset abnormal medicine combinations according to the abnormal weighting coefficients to obtain weighted abnormal weight values, and taking the average of the weighted abnormal weight values and medication abnormal weight values corresponding to other medicines in the current medicine prescriptions as the medication abnormal weight values corresponding to the current medicine prescriptions;
and when the medicine prescription does not contain the preset abnormal medicine combination, taking the average of the medication abnormal weight values corresponding to various medicines in the current medicine prescription as the medication abnormal weight value corresponding to the current medicine prescription.
4. The method as claimed in claim 1, wherein before extracting the medication type data corresponding to each drug prescription from the drug usage record, inputting the medication type data into a preset isolated forest model, obtaining the medication abnormal weight values of the drugs in each drug prescription, and obtaining the medication abnormal weight values of the drug prescriptions according to the medication abnormal weight values of the drugs in each drug prescription, the method further comprises:
constructing an isolated tree corresponding to each medicine through a preset unmarked training feature set, wherein the training feature set comprises the medicine type data of each medicine prescription containing the current medicine in the historical record;
and constructing a preset isolated forest model according to the isolated tree.
5. The method of claim 1, wherein the obtaining a visit information list, counting total costs of the parametrical single-drug products for each disease category according to the visit information list, and determining whether the total costs of the parametrical single-drug products are abnormal drug costs by using a boxmap algorithm comprises:
acquiring a medical insurance information statement of a patient to be protected according to the application of the medical insurance of the claim to be settled;
according to the visit information list of the ginseng insurance people, the total cost of single medicines of the ginseng insurance people under each disease category is counted;
acquiring single medicine expense history records of insurers corresponding to various diseases, determining a box diagram corresponding to the total expense of the ginseng and insured single medicines according to the single medicine expense history records of the insurers corresponding to various diseases, and setting the total expense range of the ginseng and insured single medicines corresponding to the number of edges larger than the upper edge number of the box diagram as the expense of abnormal medicines;
and acquiring a box chart corresponding to the total cost of the ginseng and insurance individual medicines, positioning the total cost of the ginseng and insurance individual medicines in each disease category at the position of the box chart, and judging whether the total cost of the ginseng and insurance individual medicines is abnormal medicine cost.
6. The method of claim 5, wherein when the abnormal drug weight value of the existing drug prescription is in the abnormal area or the total single drug cost is the abnormal drug cost, before determining that the application for medical insurance to be settled is an abnormal application, the method further comprises:
acquiring abnormal drug weight values of the preset isolated forest model to the drug prescriptions in the historical records;
acquiring the distribution of abnormal drug-taking weight values of the traditional Chinese medicine prescriptions in each historical record;
and determining an abnormal area of the distribution of the abnormal medication weight values of the medicine prescription according to a normal distribution principle.
7. An anomalous medical insurance application detection apparatus, said apparatus comprising:
the application receiving module is used for acquiring the medical insurance application to be claim settled and extracting the medicine use record of the medical insurance application to be claim settled;
the first data extraction module is used for extracting the medication type data corresponding to each medicine prescription from the medicine usage record, inputting the medication type data into a preset isolated forest model, acquiring medication abnormal weight values of various medicines in each medicine prescription, and acquiring the medication abnormal weight values of each medicine prescription according to the medication abnormal weight values of various medicines in each medicine prescription;
the second data extraction module is used for acquiring a visit information detailed table, counting the total cost of the ginseng and insurance individual single-time medicines under each disease category according to the visit information detailed table, and judging whether the total cost of the ginseng and insurance individual single-time medicines is the cost of abnormal medicines or not by using a box chart algorithm;
and the violation judging module is used for judging that the medical insurance application to be claim settled is an abnormal application when the abnormal drug administration weight value of the drug prescription is in the abnormal area and the total cost of the single drug is the abnormal drug expense.
8. The apparatus of claim 7, wherein the first data extraction module is specifically configured to:
running the medication type data corresponding to each medicine prescription on the isolated trees corresponding to each medicine in the preset isolated forest model, and recording the path length of the medication type data in the running process;
determining medication abnormal weight values corresponding to various medicines in the medicine prescriptions according to the path lengths;
and acquiring the medication abnormity weight values corresponding to the medicine prescriptions according to the medication abnormity weight values corresponding to the medicines in the medicine prescriptions.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. 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 method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910971925.3A CN110781222A (en) | 2019-10-14 | 2019-10-14 | Abnormal medical insurance application detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910971925.3A CN110781222A (en) | 2019-10-14 | 2019-10-14 | Abnormal medical insurance application detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110781222A true CN110781222A (en) | 2020-02-11 |
Family
ID=69385337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910971925.3A Pending CN110781222A (en) | 2019-10-14 | 2019-10-14 | Abnormal medical insurance application detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110781222A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112035543A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying abnormality of medicine usage data and computer equipment |
| CN112289403A (en) * | 2020-10-19 | 2021-01-29 | 浙江大学山东工业技术研究院 | Method and device for detecting abnormal medicine purchase of medical insurance based on two-stage screening process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876634A (en) * | 2018-06-14 | 2018-11-23 | 四川久远银海软件股份有限公司 | A kind of cost information screening technique and device |
| CN109359966A (en) * | 2018-07-25 | 2019-02-19 | 西北工业大学 | A kind of method and apparatus of detection logistics package charging exception |
| CN109376381A (en) * | 2018-09-10 | 2019-02-22 | 平安科技（深圳）有限公司 | Method for detecting abnormality, device, computer equipment and storage medium are submitted an expense account in medical insurance |
| CN109545317A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
| CN109636623A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data method for detecting abnormality, device, equipment and storage medium |
-
2019
- 2019-10-14 CN CN201910971925.3A patent/CN110781222A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876634A (en) * | 2018-06-14 | 2018-11-23 | 四川久远银海软件股份有限公司 | A kind of cost information screening technique and device |
| CN109359966A (en) * | 2018-07-25 | 2019-02-19 | 西北工业大学 | A kind of method and apparatus of detection logistics package charging exception |
| CN109376381A (en) * | 2018-09-10 | 2019-02-22 | 平安科技（深圳）有限公司 | Method for detecting abnormality, device, computer equipment and storage medium are submitted an expense account in medical insurance |
| CN109636623A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data method for detecting abnormality, device, equipment and storage medium |
| CN109545317A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112035543A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying abnormality of medicine usage data and computer equipment |
| CN112289403A (en) * | 2020-10-19 | 2021-01-29 | 浙江大学山东工业技术研究院 | Method and device for detecting abnormal medicine purchase of medical insurance based on two-stage screening process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10679299B2 (en) | Machine learning risk factor identification and mitigation system | |
| CN108615119B (en) | Abnormal user identification method and equipment | |
| US11670100B2 (en) | Method and apparatus for recognition of patient activity | |
| CN107731270A (en) | A kind of method and device of automatic examination ＆ verification prescription accuracy | |
| CN109522400B (en) | Nuclear protection method, device, computer equipment and storage medium | |
| CN109545317A (en) | The method and Related product of behavior in hospital are determined based on prediction model in hospital | |
| CN107657536A (en) | The recognition methods of social security fraud and device | |
| CN104182824A (en) | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations | |
| WO2020082788A1 (en) | Medical data processing method, apparatus and device, and storage medium | |
| CN110781222A (en) | Abnormal medical insurance application detection method and device, computer equipment and storage medium | |
| US20210326995A1 (en) | Claim settlement anti-fraud method, apparatus, device, and storage medium based on graph computation technology | |
| CN109542923B (en) | Nuclear protection method, device, computer equipment and storage medium | |
| CN109636652A (en) | Purchase monitoring method, monitoring service end and the storage medium of medicine abnormal behavior | |
| CN110729054B (en) | Abnormal diagnosis behavior detection method and device, computer equipment and storage medium | |
| CN109858735A (en) | Consumer's risk scoring assessment method, device, computer equipment and storage medium | |
| CN109377207A (en) | The abnormal method and Related product that behavior determines of being hospitalized | |
| CN111312357A (en) | Medicine analysis method and system | |
| CN111885181B (en) | Monitoring data reporting method and device, computer equipment and storage medium | |
| CN113704731A (en) | Hospital-oriented patient abnormal hospitalizing behavior detection method and system | |
| CN109493108B (en) | Medical activity information processing method, device, computer equipment and medium | |
| CN109508994B (en) | Business risk control method, device, computer equipment and storage medium | |
| CN111274231B (en) | Abnormal medical insurance data checking method and device, computer equipment and storage medium | |
| CN116434931A (en) | Medical behavior abnormality identification method, device, storage medium and equipment | |
| CN111063452A (en) | Medicine matching method and computer equipment | |
| CN111259089B (en) | Medical insurance data processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40022670 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220520 Address after: 518048 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200211 |