CN109616185A - The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations - Google Patents
The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations Download PDFInfo
- Publication number
- CN109616185A CN109616185A CN201811526943.2A CN201811526943A CN109616185A CN 109616185 A CN109616185 A CN 109616185A CN 201811526943 A CN201811526943 A CN 201811526943A CN 109616185 A CN109616185 A CN 109616185A
- Authority
- CN
- China
- Prior art keywords
- examination
- diagnosis
- medical institution
- preset
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000007689 inspection Methods 0.000 title claims abstract description 43
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000003745 diagnosis Methods 0.000 claims abstract description 142
- 238000011282 treatment Methods 0.000 claims abstract description 142
- 230000006399 behavior Effects 0.000 claims abstract description 46
- 239000013598 vector Substances 0.000 claims description 41
- 230000007246 mechanism Effects 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000009471 action Effects 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000002457 bidirectional effect Effects 0.000 claims description 7
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 7
- 239000002699 waste material Substances 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000011176 pooling Methods 0.000 abstract 1
- 210000004027 cell Anatomy 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 101100446506 Mus musculus Fgf3 gene Proteins 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses methods and relevant device that inspection item behavior is issued in a kind of detection in violation of rules and regulations, method includes: the diagnosis and treatment data for obtaining medical institutions and uploading, and Forecasting recognition is carried out using diagnosis and treatment data as the input of preset data identification model, to obtain diagnosis and treatment data label；The inspection number of each user within a preset time is obtained from diagnosis and treatment data label；The inspection number of any user within a preset time is judged whether there is more than frequency threshold value；When being more than frequency threshold value there are the inspection number of any user within a preset time, determine that medical institutions issue inspection item behavior in the presence of violation.The present invention is using the preset data identification model based on machine learning algorithm as prediction model, to obtain diagnosis and treatment data label；User is obtained according to diagnosis and treatment data label and checks number in medical institutions, then compared with the frequency threshold value set, to detect that medical institutions with the presence or absence of the behavior for issuing inspection item in violation of rules and regulations, reduce the waste of medical insurance risk-pooling fund, intelligent decision-making.
Description
Technical Field
The invention relates to the field of electronic information, in particular to a method and related equipment for detecting illegal opening inspection item behaviors.
Background
Medical insurance refers to social medical insurance, and is a social insurance system established by the nation and the society according to certain laws and regulations for providing basic medical requirements guarantee for workers in a guarantee range during illness. The basic medical insurance fund is composed of a pool fund and an individual account. After the user completes the treatment at the point-of-care facility, the point-of-care facility may apply a pool fund to the local community facility to pay the drug fee. Although the medical insurance system brings convenience to people, lawless persons still use the medical welfare policies given by the countries and the society, and cash-out is carried out by means of opening more inspection items when users treat, so that the waste of medical insurance overall fund is caused.
Disclosure of Invention
The invention mainly aims to provide a method and related equipment for detecting illegal opening examination item behaviors, and aims to solve the technical problem that medical insurance overall fund waste is caused by the fact that a medical institution carries out cash register through excessive opening examination items at present.
In order to achieve the above object, the present invention provides a method for detecting illegal opening inspection item behaviors, comprising the steps of:
acquiring diagnosis and treatment data uploaded by a medical institution, and performing prediction identification by taking the diagnosis and treatment data as the input of a preset data identification model to obtain a diagnosis and treatment data label;
acquiring the number of times of examination of each user in preset time from the diagnosis and treatment data label;
judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value;
and when the number of times of examination of any user in the preset time exceeds a threshold number, determining that the medical institution has illegal action of taking examination items.
Optionally, before the step of determining whether the number of times of checking by any user in the preset time exceeds a threshold, the method further includes:
acquiring the total times of examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
and multiplying the total times of the inspection items by a preset proportion to obtain a time threshold value.
Optionally, when the number of checks of any user in the preset time exceeds a threshold number, the step of determining that the medical institution has an illegal action of issuing a check item includes:
when the number of times of examination of any user in the preset time exceeds a threshold value, acquiring the historical number of times of examination of the medical institution;
according to the historical examination times of the medical institution, evaluating whether the medical institution meets the exemption condition of the times of a preset examination item;
when the medical institution does not meet the preset examination item frequency exemption condition, determining that the medical institution has an illegal action of opening examination items;
after the step of evaluating whether the medical institution meets the preset examination item frequency exemption condition, the method further comprises the following steps:
and when the medical institution meets the preset exemption condition of the times of the examination items, determining that the medical institution does not have the behavior of opening examination items in violation.
Optionally, before the step of determining whether the number of times of checking by any user in the preset time exceeds a threshold, the method further includes:
acquiring the institution level of the medical institution;
and acquiring a frequency threshold corresponding to the mechanism grade according to the mechanism grade of the medical mechanism, wherein the frequency threshold of the medical mechanism with the low mechanism grade is smaller than the frequency threshold of the medical mechanism with the high mechanism grade.
Optionally, the step of acquiring, according to the institution level of the medical institution, a number threshold corresponding to the institution level includes:
determining a frequency threshold range corresponding to the mechanism grade according to the mechanism grade of the medical mechanism;
acquiring the total times of examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
when a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is not in the time threshold range, taking the calculation result as the time threshold;
and when a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is within the time threshold range, taking the middle value of the time threshold range as the time threshold.
Optionally, after the step of determining whether the number of times of checking by any user in the preset time exceeds a threshold, the method further includes:
when the number of times of examination of each user in the preset time does not exceed a number threshold, obtaining the number of times of examination of each user in each department of the medical institution in the preset time according to the diagnosis and treatment data label;
acquiring historical examination times corresponding to each department of the medical institution, and determining an examination time threshold corresponding to each department according to the historical examination times corresponding to each department;
judging whether the checking frequency of each user in each department of the medical institution within preset time exceeds the checking frequency threshold of the corresponding department;
and when the checking frequency of any user in any department of the medical institution within the preset time exceeds the checking frequency threshold of the corresponding department, determining that the medical institution has illegal provision of the checking item behavior.
Optionally, the step of performing predictive recognition on the medical data as an input of a preset data recognition model to obtain a medical data tag includes:
screening noise text data in the diagnosis and treatment data according to a preset noise entity dictionary in a preset data recognition model to obtain standard diagnosis and treatment data;
performing word segmentation on the standard diagnosis and treatment data to obtain a plurality of diagnosis and treatment text word segments, and converting each diagnosis and treatment text word segment into a corresponding word vector;
acquiring sequences of all word vectors, and coding all the word vectors through a bidirectional Recurrent Neural Network (RNN) model in a preset data recognition model according to the sequence of each word vector to form a text matrix;
after the text matrix is compressed into a diagnosis and treatment text vector, prediction is carried out through a prediction network in the preset data identification model, and a diagnosis and treatment data label corresponding to the diagnosis and treatment text vector is obtained.
In addition, to achieve the above object, the present invention also provides a detection system, including:
the acquisition module is used for acquiring diagnosis and treatment data uploaded by a medical institution and performing prediction identification by taking the diagnosis and treatment data as the input of a preset data identification model to obtain a diagnosis and treatment data label;
the acquisition module is further used for acquiring the examination times of each user in preset time from the diagnosis and treatment data label;
the judging module is used for judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value;
and the determining module is used for determining that the medical institution has an illegal action of issuing examination items when the number of examination times of any user in the preset time exceeds a threshold value.
Further, to achieve the above object, the present invention also provides a detection apparatus comprising: a communication module, a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of detecting violation issuing checking item behavior as described above.
Furthermore, to achieve the above object, the present invention further provides a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method for detecting violation of a driver-checking project behavior as described above.
According to the method, diagnosis and treatment data uploaded by a medical institution are acquired, and are used as input of a preset data identification model for prediction identification, so that a diagnosis and treatment data label is obtained; acquiring the number of times of examination of each user in preset time from the diagnosis and treatment data label; judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value; and when the number of times of examination of any user in the preset time exceeds a threshold number, determining that the medical institution has illegal action of taking examination items. Therefore, on the basis that the preset data identification model based on the machine learning algorithm is used as the prediction model to obtain the diagnosis and treatment data labels, the examination times of the user in the medical institution, which are obtained according to the diagnosis and treatment data labels, are compared with the time threshold value to determine whether the medical institution has the behavior of opening examination and inspection items in violation, the behavior that the medical institution carries out cash register on the multiple examination items of the user can be found, the waste of medical insurance overall fund is reduced, and the decision is very intelligent.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a method for detecting illegal opening inspection item behavior according to the present invention;
FIG. 3 is a flowchart illustrating another embodiment of a method for detecting illegal opening inspection item behavior according to the present invention;
FIG. 4 is a flowchart illustrating a step S10 of another embodiment of the method for detecting illegal opening inspection item behavior according to the present invention;
FIG. 5 is a block diagram of an embodiment of a detection system according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a detection device 100 according to the present invention, where the detection device 100 may be at least one of a server, a computer, and a device dedicated for abnormality detection of a medical institution, and includes components such as a communication module 10, a memory 20, and a processor 30. Wherein, the processor 30 is connected to the memory 20 and the communication module 10, respectively, and the memory 20 stores thereon a computer program, which is executed by the processor 30 at the same time.
The communication module 10 may be connected to an external device through a network. The communication module 10 may receive a request from an external communication device, and may broadcast and transmit an event, an instruction, and information of the information acquisition apparatus to the external communication device. The external communication equipment can be other detection equipment or a medical institution terminal. It should be noted that the medical institution terminal is a terminal used by a medical institution staff for uploading medical data, may be a settlement terminal for calculating medical expenses, may be a terminal for issuing medical prescriptions and/or checking inspection items, and may be an autonomous registration payment service terminal.
The memory 20 may be used to store software programs as well as various data. The memory 20 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (for example, receiving medical data uploaded by a medical institution), and the like; the storage data area may store data or information created according to the use of the detection apparatus 100, or the like. Further, the memory 20 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The processor 30, which is a control center of the inspection apparatus 100, connects various parts of the entire inspection apparatus 100 by using various interfaces and lines, and performs various functions of the inspection apparatus 100 and processes data by running or executing software programs and/or modules stored in the memory 20 and calling data stored in the memory 20, thereby performing overall monitoring of the inspection apparatus 100. Processor 30 may include one or more processing units; alternatively, the processor 30 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 30.
Although not shown in fig. 1, the detection apparatus 100 may further include a circuit control module electrically connected to each module to ensure the normal operation of other modules. The detection device 100 may further include a display module for displaying the detection process and the detection result of the violation.
Those skilled in the art will appreciate that the configuration of the detection device 100 shown in FIG. 1 does not constitute a limitation of the detection device 100, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
Based on the hardware structure, various embodiments of the method of the invention are provided.
Referring to fig. 2, in an embodiment of the method for detecting illegal opening inspection item behaviors of the present invention, the method for detecting illegal opening inspection item behaviors includes the steps of:
step S10, acquiring diagnosis and treatment data uploaded by a medical institution, and performing prediction and identification by taking the diagnosis and treatment data as the input of a preset data identification model to obtain a diagnosis and treatment data label;
the embodiment is applied to a third-party organization for detecting the diagnosis and treatment data, and the third-party organization can be, for example, a social medical insurance authority.
The medical institution may upload the medical data to the detection device using a terminal, for example, when the patient is settled at the medical institution after the visit or examination is completed, the settlement terminal of the medical institution uploads the medical data of the patient qualified for participation in the insurance to a server of a third-party institution. The medical data is visit data generated when a patient qualified for insurance visits and/or hospitalization in a medical institution, and may include disease diagnosis data of the patient, spending details during treatment, a list of examination items and/or medicines to be prescribed, and a prescription made by a doctor of the medical institution.
After the diagnosis and treatment data are obtained, the detection device can identify and match the diagnosis and treatment data to the corresponding standardized fields through the preset data identification model in the memory to obtain diagnosis and treatment data labels, each diagnosis and treatment data label can be a real numerical value, a vector or a category label and the like, and the content corresponding to the diagnosis and treatment data can be identified through the diagnosis and treatment data labels. The preset data recognition model is constructed based on machine learning, and relates to technologies such as a neural network, natural language processing and an attention mechanism.
Step S20, obtaining the number of times of examination of each user in the preset time from the diagnosis and treatment data label;
the diagnosis and treatment data labels obtained through prediction and identification of the diagnosis and treatment data and the preset data identification model can be multiple, and each diagnosis and treatment data label can represent a part of or all diagnosis and treatment data contents of a medical institution in one dimension. All the diagnosis and treatment data labels in the dimension of the examination items prescribed by the medical institution can be selected from the diagnosis and treatment data labels, and the examination times of each user in the medical institution in the preset time can be obtained according to the diagnosis and treatment data labels. Wherein the predetermined time may be one week, one month, one quarter, or one year. Of course, the preset time can also be set according to the detection time of the third-party institution.
Step S30, judging whether the checking times of any user in the preset time exceeds the threshold value;
since the medical institution often realizes arbitrage by opening more examination items for users, the higher the number of examination of one user is, the higher the possibility that the medical institution has illegal action of opening examination items is. Therefore, a threshold number of times can be set, and the threshold number of times is compared with the number of times of examination for each user in a medical institution, so as to confirm whether or not the medical institution performs a profit-setting operation by giving an illegal provision of an examination item.
The number threshold may be set according to actual needs, for example, determined according to the number of provinces and/or frequent population of a city where the medical institution is located, determined according to the institution level of the medical institution, or determined according to the popularity or the historical examination number of the medical institution.
For example, the setting process of the number threshold may include the following steps:
acquiring the total times of examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
the total number of examination items of the medical institution is a result obtained by adding all examination times of all departments of all users in a preset time, and represents the number of examination items of the medical institution in a certain preset time. In the present embodiment, the examination data is obtained according to all the clinical data tags in the dimension of issuing examination items, or the examination times of all the users in a preset time may be added.
And multiplying the total times of the inspection items by a preset proportion to obtain a time threshold value.
It should be noted that the preset ratio is set by the third party according to actual needs, and generally, the preset ratio corresponding to all medical institutions is the same, for example, the preset ratio is 80%, and when the total number of times of the examination items is equal to 400, the number threshold is equal to 400 × 80% — 320. Whether the checking times of a single user exceed the standard or not is measured through the total times of the acquired checking items, and the illegal behaviors of excessive checking times generated by medical institutions in the checking process of some users can be highlighted.
And step S40, when the number of times of examination of any user in the preset time exceeds a threshold number, determining that the medical institution has illegal action of issuing examination items.
If the number of times of examination of any user in the preset time exceeds the threshold number of times, the medical institution is considered to perform arbitrage behavior by opening examination items according to the information of the user, and the medical institution opening the examination items is confirmed to have illegal action of opening the examination items. And when the judgment result of the step S30 is that the number of times of examination of all users in the preset time does not exceed the number threshold, determining that the medical institution does not have the behavior of violation of issuing examination items.
According to the embodiment, diagnosis and treatment data uploaded by a medical institution are acquired and used as input of a preset data identification model for prediction and identification, so that a diagnosis and treatment data label is obtained; acquiring the number of times of examination of each user in preset time from the diagnosis and treatment data label; judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value; and when the number of times of examination of any user in the preset time exceeds a threshold number, determining that the medical institution has illegal action of taking examination items. Therefore, on the basis that the preset data identification model based on the machine learning algorithm is used as the prediction model to obtain the diagnosis and treatment data labels, the examination times of the user in the medical institution, which are obtained according to the diagnosis and treatment data labels, are compared with the time threshold value to determine whether the medical institution has the behavior of opening examination and inspection items in violation, the behavior that the medical institution carries out cash register on the more examination items of the user can be found, the waste of medical insurance overall planning funds is reduced, and the decision is intelligent.
Optionally, when the number threshold is used for detection, the following abnormality recognition algorithm may be used for detection, including: dividing all diagnosis and treatment data labels related to the opening examination items obtained through a preset data identification model as a data space, wherein the side length of the data space is equal to d/(2 x k)1/2) The unit (2). Each cell having two layers surrounding it, the first layer having a thickness of one cell and the second layer having a thickness of int 2 k1/2-1]. The algorithm counts outliers on a cell-by-cell basis rather than on an object-by-object basis. For a given cell, it accumulates three counts: the number of objects in the cell (cell _ count), the number of cells and objects in the first layer (cell _ +_1_ layer _ count), the number of cells and objects in the two layers (cell _ +_2_ layers _ count). If cell _ +_1_ layer _ count>M, all objects in a cell are not abnormal; if cell _ + _2_ layers _ count<All objects in a cell are abnormal; otherwise, some of the data in the cell may be anomalous. The algorithm changes the detection of the abnormal point data of each element in the data space into the detection of the abnormal point data of each unit, thereby improving the efficiency of abnormal recognition.
Further, in other embodiments, the step S40 includes:
step S41, when the number of times of examination of any user in the preset time exceeds a threshold value, acquiring the historical number of times of examination of the medical institution; evaluating whether the medical institution meets the exemption condition of the times of preset inspection items or not according to the historical inspection times of the medical institution; if not, go to step S42; if yes, go to step S43;
the number of medical institution examinations acquired may be the number of medical institution examinations over the years. The condition of exemption of the number of times of the preset examination items can be set according to actual needs, for example, the number of times of the examination items of the medical institution does not exceed a first preset limit value in the last 5 years, or the number of times of the month average examination items of the medical institution does not exceed a second preset limit value in the past years, and the like.
Step S42, determining that the medical institution has illegal opening examination item behaviors;
if the medical institution does not meet the exemption condition, the medical institution is not considered to be the medical institution in a special position or under the special condition, and the number of times of examination of any user in the medical institution within the preset time exceeds the threshold number of times, so that the medical institution has the behavior of violating the examination item.
Step S43, determining that the medical institution does not have the illegal opening examination item behavior.
Because the medical institution meets the exemption condition, the medical institution can be considered as a medical institution at a special position or under a special condition, and the condition that the number of times of examination exceeds the threshold number of times possibly exists in a certain patient due to the requirements of the disease condition. The number threshold is determined by multiplying the total number of examinations in a preset time by a preset proportion in the medical institution, and the overall examination base number of the medical institution is small, so that once a certain patient needs to be detected for many times due to the condition, the examination number of the patient is easily larger than the number threshold.
And further acquiring a diagnosis report of the patient, determining whether the suspicion of the illegal opening examination item behaviors can be eliminated, and if the medical institution determines that the medical institution does not need to open the examination for the patient for multiple times according to the diagnosis report of the patient, determining that the illegal opening examination item behaviors exist in the medical institution. Otherwise, the behavior that the medical institution illegally opens the examination item is eliminated. Through presetting the exemption conditions of the times of the examination items, the number of the annual examination times of the medical institution which helps to eliminate special conditions is small, so that the condition that the number of times of the annual examination of part of patients exceeds the threshold value of the times of the annual examination is needed to be examined for many times due to the disease conditions, and the condition that the detection is inaccurate due to the occurrence of the special conditions is prevented.
Further, referring to fig. 3, in another embodiment, before the step S30, the method further includes:
step S21, acquiring the institution level of the medical institution;
the institution level of the medical institution may be an index for the state or region to evaluate the hospital qualification according to the hospital function, facility, technical strength, etc., for example, the medical institution in the continental area of china is classified into three grades and ten grades through evaluation.
In this embodiment, the method for acquiring the institution level of the medical institution may be to acquire a name or a font size of the medical institution, and search for the institution level of the medical institution from a preset database according to the name or the font size, where the preset database stores all the names/font sizes of the medical institution and corresponding institution levels. Alternatively, the institution level of the medical institution may be known from the medical institution's website and referral.
Step S22, acquiring a frequency threshold corresponding to the institution level according to the institution level of the medical institution, wherein the frequency threshold of the medical institution with low institution level is smaller than the frequency threshold of the medical institution with high institution level.
The corresponding times threshold value may be set in advance according to all the institution levels, and then the times threshold value of the medical institution may be obtained after confirming the institution level of the medical institution. It can be understood that, because the medical institutions integrating the functions, facilities and technical strength of the hospital are advanced, there is a great difference in the practical aspect compared with the medical institutions with low institution level, so that the user is more willing to select the medical institution with high institution level in the medical treatment process, and therefore, the higher the institution level of the medical institution in the actual operation process is, the larger the corresponding time threshold value is. The technical scheme of this embodiment is favorable to carrying out different number of times threshold value to the medical institution of different mechanism grades and prescribes a limit, has increased the humanized setting of check out test set, also more closely detects actual conditions.
Alternatively, the number threshold may be further set in combination with the province of the medical institution, that is, the number threshold of the examination items may be different for medical institutions of the same level in different provinces. For example, the threshold number of times in a medical facility with a large province of the standing population must be greater than the province with a small number of standing populations. Furthermore, the threshold value of the times of opening examination items of the famous hospital can be increased. The further protection of the scheme is beneficial to reasonably dividing the times threshold of the examination items aiming at medical institutions of various regions and grades.
The above step S22 may include the steps of:
step S221, determining a frequency threshold range corresponding to the mechanism grade according to the mechanism grade of the medical mechanism;
the scheme is that the mechanism grade and the total times of the inspection items in the preset time are combined to further determine the threshold value of the times. Each different institution level corresponds to a preset threshold range of times, which may be determined by collecting historical data of all medical institutions corresponding to the institution level.
Step S222, acquiring the total times of examination items of the medical institution in the preset time according to the diagnosis and treatment data label; judging whether a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is within the time threshold value range or not; if not, go to step S223; if yes, go to step S224;
in practice, the total number of times of checking items in a preset time is used as a first priority reference factor for determining the threshold value of times, and the threshold range of times determined by historical data is used as a second priority reference factor. The number threshold may be determined by first multiplying the total number of examination items of the medical institution within a preset time by a preset ratio and then comparing the calculated product with the number threshold range.
Step S223, using the calculation result as the number threshold;
step S224, using the middle value of the frequency threshold range as the frequency threshold.
And if the calculation result is not in the range of the time threshold value, determining the time threshold value by using the first priority reference factor, namely using the calculation result as the time threshold value. And if the calculation result is within the frequency threshold range, correcting the calculation result by combining a second priority reference factor, namely taking the middle value of the frequency threshold range as the frequency threshold. The setting of the frequency threshold value is more accurate and appropriate by setting two reference factors of the frequency threshold value.
Optionally, with continuing reference to fig. 2, in another embodiment, after step S30, the method further includes:
step S50, when the number of times of examination of each user in the preset time does not exceed the threshold value of the number of times, obtaining the number of times of examination of each user in each department of the medical institution in the preset time according to the diagnosis and treatment data label;
this embodiment is a further comparison operation performed after comparing the number of overall examinations of each user at the medical institution. The examination times of each user in different departments in the dimension of the prescribed examination item can be obtained according to the diagnosis and treatment data label.
Step S60, acquiring historical examination times corresponding to each department of the medical institution, and determining an examination time threshold corresponding to each department according to the historical examination times corresponding to each department;
the historical examination times of each department of the medical institution can be directly obtained according to the diagnosis and treatment data labels of the medical institution in the past year, and can also be obtained according to report data disclosed by the medical institution. The setting of the inspection frequency threshold corresponding to each department may be set according to actual needs, for example, the historical inspection frequency of the last year of the last N years is selected, where N is an integer greater than 1, and the average value of the historical inspection frequency of the last year is taken as the inspection frequency threshold. Alternatively, the historical examination frequency of a department of N years may be randomly extracted, and the maximum value of the historical examination frequency may be used as the examination frequency threshold of the department. Alternatively, the result obtained by multiplying the average value or the maximum value of the obtained historical inspection times by a preset ratio may be used as the inspection time threshold.
Step S70, judging whether the checking frequency of each user in each department of the medical institution within the preset time exceeds the checking frequency threshold of the corresponding department;
step S80, when the number of times of examination of any user in any department of the medical institution exceeds the threshold value of the number of times of examination of the corresponding department within the preset time, determining that the medical institution has the behavior of illegal release examination items.
After the threshold of the number of times of examination in each department is determined, the processor of the detection device may compare the number of times of examination in each department of each user one by one, and as long as there is a fact that the number of times of examination in any department of one user exceeds the threshold of the number of times of examination in the department, it is considered that the medical institution has a behavior of violating the provision of examination items, and the department where the violation exists is the department where the number of times of examination in the preset time of the user exceeds the threshold of the number of times of examination in the process of comparing the number of times one by one.
According to the scheme, on the premise of comparing the overall examination times, the set examination time threshold of each department is compared with the examination times of each user in the department, and whether behaviors of illegal issuing examination items exist in each department of the medical institution or not is confirmed. The illegal action of a medical institution can be found in time, the waste of medical overall fund is reduced, the detection coverage range is wide, and the illegal action occurrence position can be found quickly.
Further, referring to fig. 4, in a further embodiment, the step S10 includes:
step S11, acquiring diagnosis and treatment data uploaded by a medical institution;
the implementation process of acquiring the diagnosis and treatment data uploaded by the medical institution in this embodiment is the same as that in the foregoing embodiment, and is not described herein again.
Step S12, according to a preset noise entity dictionary in a preset data recognition model, screening noise text data in the diagnosis and treatment data to obtain standard diagnosis and treatment data;
the preset noise entity dictionary is obtained by training in advance, and noise text data, such as a mark-up symbol, a comment text and js (javascript) code, is stored in the preset noise entity dictionary. And iterating the diagnosis and treatment data according to the noise entity dictionary to eliminate the noise text data in the diagnosis and treatment data, namely outputting standard diagnosis and treatment data of the noise-free text data, and realizing the standard text field matching of the diagnosis and treatment data.
Step S13, performing word segmentation on the standard diagnosis and treatment data to obtain a plurality of diagnosis and treatment text word segments, and converting each diagnosis and treatment text word segment into a corresponding word vector;
the standard diagnosis and treatment data is a diagnosis and treatment text after noise elimination, the diagnosis and treatment text can be segmented into a plurality of diagnosis and treatment text segmentation words through word segmentation, and all diagnosis and treatment text segmentation words form a diagnosis and treatment text segmentation word set. The method for segmenting the standard diagnosis and treatment data can be executed by referring to the existing segmentation tools and segmentation algorithms, and is not described herein in detail.
After the standard diagnosis and treatment data are segmented, the diagnosis and treatment text segmentation can be subjected to word variant classification. Word variant classification refers to converting all differences of a clinical text participle into a standardized format. For example, words or words which do not exist in the standard semantic dictionary can be found from all diagnosis and treatment text participles and deleted or corrected by utilizing a preset standard semantic dictionary through a regular expression or manually writing dictionary fields. The word variant classification of all diagnosis and treatment text participles helps to better and more quickly identify the semantics of diagnosis and treatment data, and text standardization is realized.
In this embodiment, the diagnosis and treatment text participles may be vectorized to obtain a Word vector (Word embedding) corresponding to each diagnosis and treatment text participle. The word vector is a vector in which diagnosis and treatment text participles are mapped to real numbers, and can represent words and consider semantic distance.
Step S14, acquiring sequences of all word vectors, and coding all the word vectors through a bidirectional Recurrent Neural Network (RNN) model in a preset data recognition model according to the sequences of all the word vectors to form a text matrix;
the sequence of word vectors can be analogized to the arrangement sequence, in the scheme, a bidirectional RNN (recurrent neural Network) model is utilized, the sequence of sentences in the diagnosis and treatment text is taken as reference, and the word vectors after splitting and conversion are recoded and combined to form a text matrix. Each row of this text matrix represents the meaning of each word expressed in context, corresponding to a word vector.
The bidirectional RNN model is a neural network for processing sequence data, right connection can be established among neurons between layers, and after forward calculation and reverse calculation of word vectors in each line are carried out through the bidirectional RNN model, combined word vectors can be spliced according to the sequence of the word vectors corresponding to the original diagnosis and treatment text participles to obtain a complete text matrix or a sentence vector matrix.
Step S15, after compressing the text matrix into a diagnosis and treatment text vector, predicting through a prediction network in the preset data recognition model to obtain a diagnosis and treatment data label corresponding to the diagnosis and treatment text vector.
The text matrix can be compressed into diagnosis and treatment text vectors, and then the diagnosis and treatment text vectors are sent into a prediction network for prediction, so that the diagnosis and treatment data labels are obtained through learning. It should be noted that the diagnosis and treatment data label may be a series of data obtained by understanding the diagnosis and treatment text by the model, and the data may be divided into each diagnosis and treatment data label in the form of data generation time, and may be sorted by combining information of the user, the patient, and the like.
The prediction network can adopt a standard feedforward neural network structure, a recurrent neural network structure and the like. The simple prediction process of the scheme is to input the standardized field into an LTSM (Long Short-Term Memory network) to output continuous label characteristics, and the continuous label characteristics are operated through a feedforward neural network; meanwhile, the diagnosis and treatment text vector is also transmitted to a feedforward neural network to extract vector characteristics, and then the vector characteristics and the label characteristics are cascaded to form vector-label characteristics; and finally combining the vector-label combination characteristics with a diagnosis and treatment data label for prediction output.
According to the scheme, after noise is removed and diagnosis and treatment data are segmented and vectorized, the diagnosis and treatment data labels are obtained through encoding and prediction through a neural network according to a word vector sequence, the process of obtaining the diagnosis and treatment data labels through prediction and recognition through a preset data recognition model is given, diagnosis and treatment data including contents such as prescriptions issued by doctors, issued examination items and/or drug lists are matched into corresponding standardized fields, and the meaning of words in the diagnosis and treatment data in the text is reflected.
The invention also provides a detection system, which can be at least one of a server, a computer and equipment specially used for detecting the abnormality of the medical institution; referring to fig. 5, in one embodiment, the detection system includes:
the acquisition module 10 is configured to acquire diagnosis and treatment data uploaded by a medical institution, and perform predictive identification on the diagnosis and treatment data as an input of a preset data identification model to obtain a diagnosis and treatment data label;
the obtaining module 10 is further configured to obtain, from the diagnosis and treatment data tag, the number of times of examination of each user within a preset time;
a judging module 20, configured to judge whether the number of times of checking by any user in the preset time exceeds a threshold;
and the determining module 30 is used for determining that the medical institution has an illegal action of issuing examination items when the number of examination times of any user in the preset time exceeds a threshold value.
Optionally, in another embodiment, the detection system further comprises a calculation module; wherein,
the acquisition module is further used for acquiring the total times of the examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
and the calculating module is used for multiplying the total times of the checking items by a preset proportion to obtain a time threshold value.
Optionally, in a further embodiment, the determining module comprises;
a first acquisition unit, configured to acquire a historical examination count of the medical institution when there is an examination count of any user within the preset time that exceeds a count threshold;
the evaluation unit is used for evaluating whether the medical institution meets the exemption condition of the preset inspection item times according to the historical inspection times of the medical institution;
the first determination unit is used for determining that the medical institution has illegal action of opening examination items when the medical institution does not meet the preset examination item frequency exemption condition; and when the medical institution meets the preset exemption condition of the times of the examination items, determining that the medical institution does not have the behavior of opening examination items in violation.
Optionally, in a further embodiment, the obtaining module is further configured to obtain an institution level of the medical institution; and acquiring a frequency threshold corresponding to the mechanism grade according to the mechanism grade of the medical mechanism, wherein the frequency threshold of the medical mechanism with the low mechanism grade is smaller than the frequency threshold of the medical mechanism with the high mechanism grade.
Optionally, in a further embodiment, the obtaining module includes:
the second determination unit is used for determining a frequency threshold range corresponding to the mechanism grade according to the mechanism grade of the medical mechanism;
the second acquisition unit is used for acquiring the total times of the examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
the execution unit is used for taking the calculation result as the frequency threshold value when the calculation result obtained by multiplying the total frequency of the check items by a preset proportion is not in the frequency threshold value range; and when a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is within the time threshold range, taking the middle value of the time threshold range as the time threshold.
Alternatively, in yet another embodiment,
the obtaining module is further configured to obtain, according to the diagnosis and treatment data tag, the number of examinations of each user in each department of the medical institution within the preset time when the number of examinations of each user within the preset time does not exceed a number threshold;
the acquisition module is further used for acquiring historical examination times corresponding to each department of the medical institution and determining an examination time threshold corresponding to each department according to the historical examination times corresponding to each department;
the judging module is further used for judging whether the checking frequency of each user in each department of the medical institution within the preset time exceeds the checking frequency threshold of the corresponding department;
the determining module is further configured to determine that the medical institution has a violation of a provision of the examination item behavior when the number of examination of any user in any department of the medical institution exceeds the threshold of the number of examination of the corresponding department within a preset time.
Optionally, in a further embodiment, the obtaining module includes:
the screening unit is used for screening noise text data in the diagnosis and treatment data according to a preset noise entity dictionary in a preset data recognition model so as to obtain standard diagnosis and treatment data;
the word segmentation conversion unit is used for segmenting the standard diagnosis and treatment data to obtain a plurality of diagnosis and treatment text word segmentations and converting each diagnosis and treatment text word segmentation into a corresponding word vector;
the encoding unit is used for acquiring sequences of all word vectors, and encoding all the word vectors through a bidirectional Recurrent Neural Network (RNN) model in a preset data identification model according to the sequences of all the word vectors to form a text matrix;
and the prediction unit is used for predicting through a prediction network in the preset data identification model after compressing the text matrix into a diagnosis and treatment text vector to obtain a diagnosis and treatment data label corresponding to the diagnosis and treatment text vector.
The invention also proposes a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be the Memory 20 in the detection apparatus 100 of fig. 1, and may also be at least one of a ROM (Read-Only Memory)/RAM (Random Access Memory), a magnetic disk, and an optical disk, and the computer-readable storage medium includes several instructions to enable a terminal device (which may be a mobile phone, a computer, a server, or a network device) having a processor to execute the method according to the embodiments of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only an alternative embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for detecting an illegal opening examination item behavior, comprising the steps of:
acquiring diagnosis and treatment data uploaded by a medical institution, and performing prediction identification by taking the diagnosis and treatment data as the input of a preset data identification model to obtain a diagnosis and treatment data label;
acquiring the number of times of examination of each user in preset time from the diagnosis and treatment data label;
judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value;
and when the number of times of examination of any user in the preset time exceeds a threshold number, determining that the medical institution has illegal action of taking examination items.
2. The method for detecting illegal opening examination item behaviors according to claim 1, wherein before the step of judging whether the number of examination times of any user in the preset time exceeds a number threshold, the method further comprises:
acquiring the total times of examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
and multiplying the total times of the inspection items by a preset proportion to obtain a time threshold value.
3. The method of detecting an illegal claim examination item behavior, according to claim 2, wherein the step of determining that the medical institution has an illegal claim examination item behavior when the number of examinations of any user within the preset time exceeds a number threshold comprises:
when the number of times of examination of any user in the preset time exceeds a threshold value, acquiring the historical number of times of examination of the medical institution;
according to the historical examination times of the medical institution, evaluating whether the medical institution meets the exemption condition of the times of a preset examination item;
when the medical institution does not meet the preset examination item frequency exemption condition, determining that the medical institution has an illegal action of opening examination items;
after the step of evaluating whether the medical institution meets the preset examination item frequency exemption condition, the method further comprises the following steps:
and when the medical institution meets the preset exemption condition of the times of the examination items, determining that the medical institution does not have the behavior of opening examination items in violation.
4. The method for detecting illegal opening examination item behaviors according to claim 1, wherein before the step of judging whether the number of examination times of any user in the preset time exceeds a number threshold, the method further comprises:
acquiring the institution level of the medical institution;
and acquiring a frequency threshold corresponding to the mechanism grade according to the mechanism grade of the medical mechanism, wherein the frequency threshold of the medical mechanism with the low mechanism grade is smaller than the frequency threshold of the medical mechanism with the high mechanism grade.
5. The method for detecting illegal opening examination item behaviors according to claim 4, wherein the step of obtaining a number threshold corresponding to the institution level according to the institution level of the medical institution comprises:
determining a frequency threshold range corresponding to the mechanism grade according to the mechanism grade of the medical mechanism;
acquiring the total times of examination items of the medical institution within the preset time according to the diagnosis and treatment data label;
when a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is not in the time threshold range, taking the calculation result as the time threshold;
and when a calculation result obtained by multiplying the total times of the inspection items by a preset proportion is within the time threshold range, taking the middle value of the time threshold range as the time threshold.
6. The method for detecting illegal opening examination item behaviors according to claim 1, wherein after the step of judging whether the number of examination times of any user in the preset time exceeds a number threshold, the method further comprises:
when the number of times of examination of each user in the preset time does not exceed a number threshold, obtaining the number of times of examination of each user in each department of the medical institution in the preset time according to the diagnosis and treatment data label;
acquiring historical examination times corresponding to each department of the medical institution, and determining an examination time threshold corresponding to each department according to the historical examination times corresponding to each department;
judging whether the checking frequency of each user in each department of the medical institution within preset time exceeds the checking frequency threshold of the corresponding department;
and when the checking frequency of any user in any department of the medical institution within the preset time exceeds the checking frequency threshold of the corresponding department, determining that the medical institution has illegal provision of the checking item behavior.
7. The method for detecting illegal opening examination item behaviors according to any one of claims 1 to 6, wherein the step of performing predictive recognition on the diagnosis and treatment data as an input of a preset data recognition model to obtain diagnosis and treatment data labels comprises the following steps of:
screening noise text data in the diagnosis and treatment data according to a preset noise entity dictionary in a preset data recognition model to obtain standard diagnosis and treatment data;
performing word segmentation on the standard diagnosis and treatment data to obtain a plurality of diagnosis and treatment text word segments, and converting each diagnosis and treatment text word segment into a corresponding word vector;
acquiring sequences of all word vectors, and coding all the word vectors through a bidirectional Recurrent Neural Network (RNN) model in a preset data recognition model according to the sequence of each word vector to form a text matrix;
after the text matrix is compressed into a diagnosis and treatment text vector, prediction is carried out through a prediction network in the preset data identification model, and a diagnosis and treatment data label corresponding to the diagnosis and treatment text vector is obtained.
8. A detection system, comprising:
the acquisition module is used for acquiring diagnosis and treatment data uploaded by a medical institution and performing prediction identification by taking the diagnosis and treatment data as the input of a preset data identification model to obtain a diagnosis and treatment data label;
the acquisition module is further used for acquiring the examination times of each user in preset time from the diagnosis and treatment data label;
the judging module is used for judging whether the checking frequency of any user in the preset time exceeds a frequency threshold value;
and the determining module is used for determining that the medical institution has an illegal action of issuing examination items when the number of examination times of any user in the preset time exceeds a threshold value.
9. A detection device, characterized in that the detection device comprises: a communication module, a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of detecting violation claim checking item behavior according to any of claims 1-7.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of detecting violation issuing checking item behavior according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811526943.2A CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811526943.2A CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109616185A true CN109616185A (en) | 2019-04-12 |
Family
ID=66007676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811526943.2A Pending CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109616185A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672864A (en) * | 2019-06-26 | 2020-01-10 | 金寓润泽(北京)科技有限责任公司 | Clinical medical body fluid detection quality control method, device and system |
| CN110727711A (en) * | 2019-10-14 | 2020-01-24 | 平安医疗健康管理股份有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
| WO2021068601A1 (en) * | 2019-10-12 | 2021-04-15 | 平安国际智慧城市科技股份有限公司 | Medical record detection method and apparatus, device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704961A (en) * | 2004-05-26 | 2005-12-07 | 冲博子 | Analysis method for diagnosis and treatment behavior and administration |
| CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
| CN103514576A (en) * | 2013-09-06 | 2014-01-15 | 深圳民太安信息技术有限公司 | Screening method for illegal cashing of social security treatment |
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
| CN107123072A (en) * | 2017-05-11 | 2017-09-01 | 杭州逸曜信息技术有限公司 | Medical expense restriction rule generation method |
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| CN108022635A (en) * | 2017-11-01 | 2018-05-11 | 平安科技（深圳）有限公司 | Violation document methods of marking, violation document scoring apparatus and computer-readable recording medium |
| CN108648810A (en) * | 2018-05-11 | 2018-10-12 | 平安医疗健康管理股份有限公司 | Data processing method, device and the computer readable storage medium of medicine audit |
| CN108960463A (en) * | 2018-06-28 | 2018-12-07 | 厦门安盟网络股份有限公司 | Reserving method, medium, terminal device and the system of medical examination project |
-
2018
- 2018-12-13 CN CN201811526943.2A patent/CN109616185A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704961A (en) * | 2004-05-26 | 2005-12-07 | 冲博子 | Analysis method for diagnosis and treatment behavior and administration |
| CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
| CN103514576A (en) * | 2013-09-06 | 2014-01-15 | 深圳民太安信息技术有限公司 | Screening method for illegal cashing of social security treatment |
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
| CN107123072A (en) * | 2017-05-11 | 2017-09-01 | 杭州逸曜信息技术有限公司 | Medical expense restriction rule generation method |
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| CN108022635A (en) * | 2017-11-01 | 2018-05-11 | 平安科技（深圳）有限公司 | Violation document methods of marking, violation document scoring apparatus and computer-readable recording medium |
| CN108648810A (en) * | 2018-05-11 | 2018-10-12 | 平安医疗健康管理股份有限公司 | Data processing method, device and the computer readable storage medium of medicine audit |
| CN108960463A (en) * | 2018-06-28 | 2018-12-07 | 厦门安盟网络股份有限公司 | Reserving method, medium, terminal device and the system of medical examination project |
Non-Patent Citations (1)
| Title |
|---|
| 朱明, 中国科学技术大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672864A (en) * | 2019-06-26 | 2020-01-10 | 金寓润泽(北京)科技有限责任公司 | Clinical medical body fluid detection quality control method, device and system |
| CN110672864B (en) * | 2019-06-26 | 2023-05-02 | 北京华视诺维医疗科技有限公司 | Quality control method, equipment and system for clinical medical body fluid detection |
| WO2021068601A1 (en) * | 2019-10-12 | 2021-04-15 | 平安国际智慧城市科技股份有限公司 | Medical record detection method and apparatus, device and storage medium |
| CN110727711A (en) * | 2019-10-14 | 2020-01-24 | 平安医疗健康管理股份有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
| CN110727711B (en) * | 2019-10-14 | 2023-10-27 | 深圳平安医疗健康科技服务有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021068601A1 (en) | Medical record detection method and apparatus, device and storage medium | |
| US20230260048A1 (en) | Implementing Machine Learning For Life And Health Insurance Claims Handling | |
| US11436269B2 (en) | System to predict future performance characteristic for an electronic record | |
| CN107833603B (en) | Electronic medical record document classification method and device, electronic equipment and storage medium | |
| JP5586373B2 (en) | Computer-readable storage medium storing a program for causing a computer system to realize the function of a component that processes a payment request, and a method of operating a computer system that causes a computer system to process a payment request | |
| CN110263157B (en) | Data risk prediction method, device and equipment | |
| US20120173289A1 (en) | System and method for detecting and identifying patterns in insurance claims | |
| CN113592019B (en) | Fault detection method, device, equipment and medium based on multi-model fusion | |
| US20210201266A1 (en) | Systems and methods for processing claims | |
| CN111444717A (en) | Method and device for extracting medical entity information, storage medium and electronic equipment | |
| CN109616185A (en) | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations | |
| CN113590824B (en) | Construction method and device of causal logic map and related equipment | |
| Ball et al. | Evaluating automated approaches to anaphylaxis case classification using unstructured data from the FDA Sentinel System | |
| CN109685670A (en) | Social security violation detection method, device, equipment and computer readable storage medium | |
| EP3847612A2 (en) | Visualization of social determinants of health | |
| CN113762973A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN113610375B (en) | Policy and insurance checking method and device based on natural language processing | |
| US20190051416A1 (en) | Processing of Patient Health Information | |
| CN117114901A (en) | Method, device, equipment and medium for processing insurance data based on artificial intelligence | |
| CN116564539A (en) | Medical similar case recommending method and system based on information extraction and entity normalization | |
| CN116311313A (en) | Medical record report form detection method, device, equipment and medium based on artificial intelligence | |
| CN114202768B (en) | Method and device for evaluating risk of insurance policy claim settlement, electronic equipment and storage medium | |
| CN115293915A (en) | Service data verification method, device, equipment and storage medium | |
| CN115760438A (en) | Digital dynamic underwriting system, method, equipment and storage medium | |
| CN109493243A (en) | A kind of disease score value method of calibration neural network based and calculate equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |