CN112734585A - Method, device, equipment and storage medium for predicting medical insurance fund expenditure - Google Patents
Method, device, equipment and storage medium for predicting medical insurance fund expenditure Download PDFInfo
- Publication number
- CN112734585A CN112734585A CN202110098229.3A CN202110098229A CN112734585A CN 112734585 A CN112734585 A CN 112734585A CN 202110098229 A CN202110098229 A CN 202110098229A CN 112734585 A CN112734585 A CN 112734585A
- Authority
- CN
- China
- Prior art keywords
- medical insurance
- sequence data
- time
- data
- expenditure
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/2474—Sequence data queries, e.g. querying versioned data
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for predicting medical insurance fund expenditure. The method comprises the following steps: acquiring first time sequence data of medical insurance fund expenditure of a first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of a second subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment; performing dimensionality reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data; and fusing the treatment characteristic sequence data and the fourth time sequence data to obtain the medical insurance fund expenditure of the second object in the target time within the preset time period after the medical insurance treatment is adjusted, wherein the medical insurance fund expenditure after the medical insurance treatment is adjusted can be accurately predicted.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method, a device, equipment and a storage medium for predicting medical insurance fund expenditure.
Background
Social medical insurance (hereinafter referred to as "medical insurance") is a degree arrangement for forcing citizens to pay and participate and compensating medical expense loss of insured people due to diseases, negative injuries, disabilities and the like through national legislation in China. In order to improve the medical security level of the whole people, medical insurance fund management departments need to continuously adjust medical insurance treatment, which inevitably influences the change of medical insurance fund expenditure.
In order to ensure the balance of medical insurance fund collection and payment and ensure the stable and sustainable operation of medical insurance fund, the medical insurance fund management department is very necessary to predict the medical insurance fund expenditure after medical insurance treatment adjustment. However, at present, a technical scheme capable of accurately predicting medical insurance fund expenditure after medical insurance treatment adjustment is not available, which is a technical problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting medical insurance fund expenditure, so as to realize the effect of accurately predicting the medical insurance fund expenditure after medical insurance treatment adjustment.
In a first aspect, an embodiment of the present invention provides a method for predicting medical insurance fund expenditure, which may include:
acquiring first time sequence data of medical insurance fund expenditure of a first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of a second subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment;
performing dimensionality reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment is adjusted.
Optionally, performing dimension reduction on the first time-series data according to the second time-series data may include:
seasonal feature sequence data generated based on seasonal variation is obtained according to the second time sequence data, and dimension reduction is carried out on the first time sequence data based on the seasonal feature sequence data.
Based on this, optionally, performing dimensionality reduction on the first time-series data based on the seasonal feature sequence data may include:
for each to-be-reduced dimensional data in the first time sequence data, determining seasonal feature data corresponding to the to-be-reduced dimensional data from the seasonal feature sequence data;
subtracting seasonal characteristic data from the dimension data to be reduced to obtain dimension-reduced data;
correspondingly, obtaining the treatment characteristic sequence data generated based on the medical insurance treatment adjustment may include:
and taking sequence data formed by the reduced dimension data corresponding to each dimension-to-be-reduced data as treatment characteristic sequence data generated based on medical insurance treatment adjustment.
Optionally, fusing the processing feature sequence data and the fourth time sequence data, which may include:
and superposing the processing characteristic sequence data on the fourth time sequence data.
On the basis, optionally, the superimposing the processing feature sequence data on the fourth time sequence data may include:
for each data to be superposed in the fourth time series data, determining the characteristic data to be superposed corresponding to the data to be superposed from the characteristic sequence data to be encountered;
superposing the characteristic data to be superposed on the data to be superposed to obtain superposed data;
correspondingly, obtaining the medical insurance fund expenditure of the second subject at the target time within the preset time period after the medical insurance treatment is adjusted may include:
and according to sequence data formed by the superposed data corresponding to the data to be superposed, medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment adjustment is obtained.
Optionally, the obtaining of the first time-series data of the medical insurance fund expenditure of the first subject who has performed the medical insurance treatment adjustment after the medical insurance treatment adjustment may include:
acquiring expenditure details of medical insurance fund expenditure of the first object subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, wherein the expenditure details comprise expenditure time and expenditure expense cost under the expenditure time;
and summarizing expenditure expenses at each expenditure time corresponding to the time interval in the expenditure details according to the preset time interval to obtain first time series data.
On this basis, optionally, the first time-series data includes sequence data in which the independent variable is a payout time and the dependent variable is a payout cost.
In a second aspect, an embodiment of the present invention further provides a device for predicting medical insurance fund expenditure, which may include:
the time sequence data acquisition module is used for acquiring first time sequence data of medical insurance fund expenditure of the first object subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, second time sequence data before the medical insurance treatment adjustment and third time sequence data of medical insurance fund expenditure of the second object to be subjected to medical insurance treatment adjustment;
the time sequence data processing module is used for reducing the dimension of the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and the medical insurance fund expenditure prediction module is used for fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object at a target time within a preset time period after medical insurance treatment is adjusted.
In a third aspect, an embodiment of the present invention further provides a device for predicting medical insurance fund expenditure, which may include:
one or more processors;
a memory for storing one or more programs;
when executed by one or more processors, cause the one or more processors to implement the method for predicting medical insurance fund expenditure provided by any of the embodiments of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for predicting medical insurance fund expenditure provided in any embodiment of the present invention.
According to the technical scheme, dimension reduction is performed on first time sequence data of medical insurance fund expenditure of a first object after medical insurance encounter adjustment through acquired second time sequence data of the medical insurance fund expenditure of the first object before the medical insurance encounter adjustment, treatment characteristic sequence data which can show that the medical insurance fund expenditure of the first object is influenced due to the medical insurance encounter adjustment can be obtained, and fourth time sequence data of the medical insurance fund expenditure of a second object to be subjected to the medical insurance encounter adjustment when the medical insurance encounter adjustment is not performed can be predicted through acquired third time sequence data of the medical insurance fund expenditure of the second object; and further fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object at a target time within a preset time period after medical insurance treatment is adjusted. According to the technical scheme, the medical insurance fund expenditure after medical insurance treatment adjustment of the second object is obtained by fusing the treatment characteristic sequence data which is extracted from the time sequence data of the first object subjected to medical insurance treatment adjustment and is generated due to medical insurance treatment adjustment to the prediction result of the medical insurance fund expenditure of the second object to be subjected to medical insurance treatment adjustment when medical insurance treatment adjustment is not carried out, and the effect of accurately predicting the medical insurance fund expenditure after medical insurance treatment adjustment is achieved.
Drawings
FIG. 1 is a flow chart of a method for predicting medical insurance fund expenditure in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of a method for predicting medical insurance fund expenditure according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a method for predicting medical insurance fund expenditure according to a third embodiment of the present invention;
FIG. 4 is a flowchart of a method for predicting medical insurance fund expenditure in a fourth embodiment of the present invention;
FIG. 5 is a block diagram showing a device for predicting medical insurance fund expenditure according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a device for predicting medical insurance fund expenditure in the sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before the embodiment of the present invention is described, an application scenario of the embodiment of the present invention is exemplarily described: at present, medical insurance fund expenditure is mainly predicted by adopting a statistical method, specifically, historical dosage and expense conditions of medical items are counted, and the change trend of the medical insurance fund expenditure or medical insurance fund expenditure after medical insurance treatment is adjusted is presumed by combining the disease incidence rate and the wage growth rate. However, the above method has the following drawbacks: a large amount of data statistics needs to be carried out manually, and the prediction result is completely based on statistical speculation, so that the cost is high and the accuracy is low.
Example one
Fig. 1 is a flowchart of a method for predicting medical insurance fund expenditure according to an embodiment of the present invention. The embodiment can be applied to the condition of predicting the medical insurance fund expenditure after medical insurance treatment adjustment. The method can be executed by the medical insurance fund expenditure prediction device provided by the embodiment of the invention, the device can be realized by software and/or hardware, and the device can be integrated with medical insurance fund expenditure prediction equipment which can be on various user terminals or servers.
Referring to fig. 1, the method of the embodiment of the present invention specifically includes the following steps:
s110, acquiring first time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment, and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment.
The first object may be an object that has been adjusted for medical insurance treatment, such as a region where the adjustment for medical insurance treatment has been performed, a hospital under a certain region, and the like. There are many ways to adjust the medical insurance treatment, such as bringing a certain medicine out of the medical insurance reimbursement range into the medical insurance reimbursement range, reducing the price of a certain medicine in the medical insurance reimbursement range, and the like. The second subject may be a subject that is ready to be administered but has not been administered the same way the adjustments to the medical insurance treatment of the first subject were performed. In practical applications, optionally, the first object and the second object may be objects on the same level, for example, the first object is a region, and the second object may also be a region; for example, if the first object is a third-level hospital in a certain area, the second object may also be a third-level hospital in a certain area; etc., and are not specifically limited herein. The advantage of such an arrangement is that the influence of the adjustment mode of the same medical insurance treatment on different levels of objects may be different, for example, the application frequency of a certain medicine in a third-level hospital is higher and the application frequency of the medicine in a second-level hospital and a first-level hospital is lower, so that the arrangement can improve the accuracy of the subsequent medical insurance basic expenditure prediction.
When the medical insurance treatment of a certain subject is adjusted, the medical insurance fund expenditure of the subject may change due to the adjustment of the medical insurance treatment. Therefore, for a first object which is subjected to medical insurance treatment adjustment, first time sequence data of medical insurance fund expenditure after the medical insurance treatment adjustment and second time sequence data of medical insurance fund expenditure before the medical insurance treatment adjustment can be respectively obtained; similarly, for the second object to be subjected to medical insurance treatment adjustment, since the second object is not yet subjected to medical insurance treatment adjustment, the acquired third time series data of medical insurance fund expenditure is the third time series data of medical insurance fund expenditure before treatment adjustment. In practical applications, optionally, the first time-series data and the third time-series data may be time-series data under the same time period, for example, the former may be time-series data of the medical insurance fund expenditure of the first object in the year 2019 and 2020, and the latter may be time-series data of the medical insurance fund expenditure of the second object in the year 2019 and 2020. Of course, both may be time series data at different time periods, and are not specifically limited herein. It should be noted that the time-series data may be series data at a series of preset time intervals, which are composed of medical insurance fund expenses sequentially acquired at different times, and in the above example, days are used as the preset time intervals, the time-series data may be series data composed of 365 data, and each data may be a total number of medical insurance fund expenses of the corresponding day.
And S120, performing dimension reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data.
Wherein, a curve composed of the data in the time series data can be obtained, and the curve can have the characteristics of trend, seasonality, periodicity and the like. In the field of medical insurance fund expenditure, time-series data is not periodic, but may be seasonal and trending. Specifically, there may be differences in the medical insurance fund expenditure each month, for example, the medical insurance fund expenditure at the beginning of the year and at the end of the year is relatively large, and the medical insurance fund expenditure in 3 months and 9 months is also relatively large due to the influence of epidemic diseases, thereby presenting a curve with seasonal medical insurance fund expenditure. In addition, the trend may be a trend of medical insurance fund expenditure caused by medical insurance treatment adjustment, for example, after a certain medicine out of the medical insurance reimbursement range is summarized to the medical insurance reimbursement range, the medical insurance fund expenditure may show an increasing trend.
It can be seen that, since the first time-series data is time-series data after medical insurance treatment adjustment, which may have seasonality and tendency, and the second time-series data is time-series data before medical insurance treatment adjustment, which may have seasonality and no tendency, the first time-series data may be dimensionality-reduced based on the second time-series data to obtain treatment feature-series data generated based on medical insurance treatment adjustment, that is, parts related to seasonality are respectively removed from each data of the first time-series data, so that parts related to tendency may be obtained, which may be referred to as treatment feature-series data, which may indicate an influence on medical insurance fund expenditure due to medical insurance treatment adjustment. In practical applications, optionally, the dimension reduction result (i.e., the treatment feature sequence data) may form a curve that is approximately a straight line, the independent variable of the curve may be time and the dependent variable may be the change of the medical insurance fund expense caused by the adjustment of the medical insurance treatment, which may indicate the change trend of the medical insurance fund expense along with the increase of the execution time of the adjusted medical insurance treatment after the adjustment of the medical insurance treatment.
It should be noted that, in the above description, the dimension reduction process is explained only by taking seasonality as an example, in practical applications, there may be many factors that may cause a change in medical insurance fund expenditure, and the changes in medical insurance fund expenditure caused by other factors except medical insurance treatment adjustment are noise that needs to be removed from the first sequence data, so as to obtain treatment feature sequence data generated only based on medical insurance treatment adjustment. The dimension reduction process can be realized based on a time series feature extraction algorithm in an artificial intelligence technology, the time series feature extraction algorithm can be an AutoEncoder model based on a neural network, and efficient feature extraction and feature representation are carried out on high-dimensional data in an unsupervised learning mode; of course, the time series feature extraction algorithm may also be other algorithms capable of performing feature extraction and feature representation on high-dimensional data, and is not specifically limited herein.
When the dimension reduction is performed on the first time series data, fourth time series data of medical insurance fund expenditure of the first object in a preset time period can be predicted according to the third time series data, wherein the preset time period can be a certain time period in the future which does not occur yet, and since the third time series data is time series data when medical insurance treatment adjustment is not performed, the predicted fourth time series data in the preset time period can be time series data which is formed by medical insurance fund expenditure which does not occur yet and has not performed medical insurance treatment adjustment. The prediction process may be implemented by a time series prediction algorithm in an artificial intelligence technology, such as an Autoregressive Integrated Moving Average Model (ARIMA), a Long Short Term Memory Network (LSTM), and the like, which is not specifically limited herein.
And S130, fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment adjustment.
Wherein, since the first time-series data and the second time-series data differ only in whether or not medical insurance treatment adjustment is performed, for a portion of the second time-series data corresponding to the first time-series data in which the time length of the time period is consistent, time-series data obtained after fusing the treatment characteristic sequence data on the basis of the portion of the time-series data is substantially consistent with the first time-series data. For example, it is assumed that the first time-series data is time-series data of medical insurance fund expenditure during the year 2019-.
On this basis, since the fourth time series data may be time series data formed by medical insurance fund expenses that have not occurred before the medical insurance treatment is adjusted (i.e., within a preset time period), new time series data formed by medical insurance fund expenses within the preset time period after the medical insurance treatment is adjusted may be obtained by fusing the above-obtained treatment feature series data to the fourth time series data, and then medical insurance fund expenses at a target time after the medical insurance treatment is adjusted within the preset time period may be obtained according to the trusted time series data, where the target time may be a time point at which there is a prediction demand for medical insurance fund expenses within the preset time period. Illustratively, continuing with the above example as an example, the new time-series data may be the time-series data with a preset time interval of days for the medical insurance fund expenditure after the medical insurance treatment adjustment during 2020-. It should be noted that, optionally, a certain confidence level may exist in the fourth time series data, and then the certain confidence level may also exist in the new time series data obtained after fusing the feature-to-be-encountered sequence data on the basis of the fourth time series data.
The "first", "second", "third", and "fourth" of the "first time-series data", "second time-series data", "third time-series data", and "fourth time-series data" are used merely to distinguish the time-series data from each other, and are not intended to specifically limit the order or content of the time-series data.
According to the technical scheme, dimension reduction is performed on first time sequence data of medical insurance fund expenditure of a first object after medical insurance encounter adjustment through acquired second time sequence data of the medical insurance fund expenditure of the first object before the medical insurance encounter adjustment, treatment characteristic sequence data which can show that the medical insurance fund expenditure of the first object is influenced due to the medical insurance encounter adjustment can be obtained, and fourth time sequence data of the medical insurance fund expenditure of a second object to be subjected to the medical insurance encounter adjustment when the medical insurance encounter adjustment is not performed can be predicted through acquired third time sequence data of the medical insurance fund expenditure of the second object; and further fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object at a target time within a preset time period after medical insurance treatment is adjusted. According to the technical scheme, the medical insurance fund expenditure after medical insurance treatment adjustment of the second object is obtained by fusing the treatment characteristic sequence data which is extracted from the time sequence data of the first object subjected to medical insurance treatment adjustment and is generated due to medical insurance treatment adjustment to the prediction result of the medical insurance fund expenditure of the second object to be subjected to medical insurance treatment adjustment when medical insurance treatment adjustment is not carried out, and the effect of accurately predicting the medical insurance fund expenditure after medical insurance treatment adjustment is achieved.
Example two
Fig. 2 is a flowchart of a method for predicting medical insurance fund expenditure according to the second embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, performing dimension reduction on the first time series data according to the second time series data may specifically include: seasonal feature sequence data generated based on seasonal variation is obtained according to the second time sequence data, and dimension reduction is carried out on the first time sequence data based on the seasonal feature sequence data. The same or corresponding terms as those in the above embodiments are not explained in detail herein.
Referring to fig. 2, the method of the present embodiment may specifically include the following steps:
s210, acquiring first time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment, and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment.
S220, seasonal feature sequence data generated based on seasonal variation is obtained according to the second time sequence data, dimension reduction is carried out on the first time sequence data based on the seasonal feature sequence data, and treatment feature sequence data generated based on medical insurance treatment adjustment are obtained.
In the medical insurance fund expenditure field, the time sequence data formed based on the medical insurance fund expenditure mainly has the characteristics of seasonality and tendency, if parts related to the seasonality can be eliminated from each data of the first time sequence data, parts related to the tendency can be obtained, and treatment characteristic sequence data generated based on medical insurance treatment adjustment can be obtained. Specifically, the second time-series data is time-series data before medical insurance treatment adjustment, and the second time-series data is not characterized by tendency caused by medical insurance treatment adjustment, but is characterized by seasonality caused by seasonal variation. Accordingly, seasonal feature sequence data generated based on seasonal variation may be derived based on the second time-series data, and this seasonal feature sequence data may indicate an influence on medical insurance fund expenditure due to the seasonal variation. Furthermore, the first time series data can be dimensionality-reduced based on the seasonal feature sequence data, namely, the part of the first time series data, which is relevant to the seasonality, is flushed away from the seasonal feature sequence data, so that the treatment feature sequence data, which is relevant to the trend, in the first time series data is obtained.
And S230, predicting fourth time series data of medical insurance fund expenditure of the second subject in a preset time period according to the third time series data.
And S240, fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment is adjusted.
According to the technical scheme of the embodiment of the invention, seasonal feature sequence data generated based on seasonal variation is extracted from second time sequence data without trend, and dimension reduction is carried out on the first time sequence data with both seasonality and trend based on the seasonal feature sequence data, so that treatment feature sequence data generated due to medical insurance treatment adjustment can be accurately extracted from the first sequence data.
On the basis, an optional technical solution is that dimension reduction is performed on the first time-series data based on the seasonal feature sequence data, and may include: for each to-be-reduced dimensional data in the first time sequence data, determining seasonal feature data corresponding to the to-be-reduced dimensional data from the seasonal feature sequence data; subtracting seasonal characteristic data from the dimension data to be reduced to obtain dimension-reduced data; correspondingly, obtaining the treatment characteristic sequence data generated based on the medical insurance treatment adjustment may include: and taking sequence data formed by the reduced dimension data corresponding to each dimension-to-be-reduced data as treatment characteristic sequence data generated based on medical insurance treatment adjustment. Wherein, since the data to be dimension reduced can be any data in the first time series data, each data to be dimension reduced has a part related to seasonality and a part related to trend, and accordingly, for each data to be dimension reduced, since the seasonal feature series data is also time series data in nature, the seasonal feature data corresponding to the data to be dimension reduced in time can be obtained from the seasonal feature series data, and exemplarily, assuming that a certain data to be dimension reduced is medical insurance fund expenditure of 1 month and 1 day, the seasonal feature data corresponding to the data to be dimension reduced can be data of 1 month and 1 day in the seasonal feature series data; furthermore, the seasonal feature data may be subtracted from the dimension-to-be-reduced data to obtain dimension-reduced data only related to the tendency, and the sequence data of each dimension-reduced data may be used as the feature-to-be-reduced sequence data generated based on medical insurance treatment adjustment. According to the technical scheme, seasonal feature data only with seasonality is subtracted from the to-be-reduced dimensional data with seasonality and tendency, and the effect that the to-be-reduced feature sequence data generated due to medical insurance treatment adjustment is obtained after dimension reduction is carried out on the first sequence data is achieved.
EXAMPLE III
Fig. 3 is a flowchart of a method for predicting medical insurance fund expenditure according to the third embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, fusing the processing feature sequence data and the fourth time sequence data, which may specifically include: and superposing the processing characteristic sequence data on the fourth time sequence data. The same or corresponding terms as those in the above embodiments are not explained in detail herein.
Referring to fig. 3, the method of this embodiment may specifically include the following steps:
s310, acquiring first time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment, and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment.
S320, performing dimension reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data.
And S330, overlapping the treatment characteristic sequence data on the fourth time sequence data to obtain the medical insurance fund expenditure of the second object at the target time within the preset time period after the medical insurance treatment is adjusted.
Wherein, since the fourth time series data is the time series data before the medical insurance treatment adjustment, it has no part related to the medical insurance treatment adjustment. In order to predict the medical insurance fund expenditure after medical insurance treatment adjustment, the treatment characteristic sequence data which can show that the medical insurance fund expenditure is influenced by the medical insurance treatment adjustment can be directly superposed on the fourth time sequence data, so that new time sequence data with a part related to the medical insurance treatment adjustment is obtained.
According to the technical scheme of the embodiment of the invention, the treatment characteristic sequence data which can show that medical insurance fund expenditure is influenced due to medical insurance treatment adjustment is directly superposed on the fourth time sequence data before medical insurance treatment adjustment, so that the effect of accurately predicting the time sequence data after medical insurance treatment adjustment is achieved.
On this basis, an optional technical solution, superimposing the sequence data of the feature to be processed on the fourth time series data, may include: for each data to be superposed in the fourth time series data, determining the characteristic data to be superposed corresponding to the data to be superposed from the characteristic sequence data to be encountered; superposing the characteristic data to be superposed on the data to be superposed to obtain superposed data; correspondingly, obtaining the medical insurance fund expenditure of the second subject at the target time within the preset time period after the medical insurance treatment is adjusted may include: and according to sequence data formed by the superposed data corresponding to the data to be superposed, medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment adjustment is obtained. Wherein, since the data to be superimposed may be any data in the fourth time series data, each data to be superimposed has a part related to trend, and accordingly, for each data to be superimposed, considering that the characteristic data to be superimposed is also time series data in nature, the characteristic data to be superimposed corresponding in time to the data to be superimposed may be obtained from the characteristic data to be superimposed, and for example, if a certain data to be superimposed is medical insurance fund expenditure of 1 month and 1 day, the characteristic data to be superimposed corresponding thereto may be data of 1 month and 1 day in the characteristic data to be superimposed; further, the processing feature data can be superimposed on the data to be superimposed to obtain superimposed data related to the tendency. Since the time-series data of the superimposed data may be time-series data constituted by predicted medical insurance fund expenses of the second subject after medical insurance treatment adjustment within the preset time period, medical insurance fund expenses of the second subject at the target time within the preset time period after medical insurance treatment adjustment may be obtained from the constituted time-series data. According to the technical scheme, the characteristic data to be processed are superposed in the corresponding data to be superposed which does not have tendency, so that superposed data which can be used for predicting the medical insurance fund expenditure after medical insurance processing adjustment in the preset time period are obtained.
Example four
Fig. 4 is a flowchart of a method for predicting medical insurance fund expenditure according to the fourth embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, the obtaining of the first time-series data of the medical insurance fund expenditure of the first subject subjected to the medical insurance treatment adjustment after the medical insurance treatment adjustment may specifically include: acquiring expenditure details of medical insurance fund expenditure of the first object subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, wherein the expenditure details comprise expenditure time and expenditure expense cost under the expenditure time; and summarizing expenditure expenses at each expenditure time corresponding to the time interval in the expenditure details according to the preset time interval to obtain first time series data. The same or corresponding terms as those in the above embodiments are not explained in detail herein.
Referring to fig. 4, the method of this embodiment may specifically include the following steps:
s410, acquiring the expenditure detail of the medical insurance fund expenditure of the first object which is subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, wherein the expenditure detail comprises expenditure time and expenditure expense under the expenditure time.
Where the expenditure may obviously be a detail obtained from the medical insurance data center indicating how much expense (i.e. expenditure expense) was paid at what time (i.e. expenditure time), and optionally, at what time and place. In practice, optionally, to achieve accurate analysis of medical insurance fund expenditure, the expenditure time in expenditure details may typically be accurate to the order of seconds.
And S420, summarizing expenditure expenses at each expenditure time corresponding to the time interval in the expenditure details according to the preset time interval to obtain first time series data.
In order to obtain the first time-series data with uniform specification, each expenditure detail may be preprocessed first, because the data source, the data representation form, and the like of each expenditure detail may not be uniform. Specifically, since the first time-series data may be time-related data related to medical insurance fund expenditure, expenditure fees at each expenditure time corresponding to the time interval in the expenditure details may be collected at a preset time interval, and then time-series data in which the collection results are formed in chronological order may be used as the first time-series data. For example, assuming that the time interval is a day, the expenditure costs at each expenditure time belonging to the same day may be aggregated, whereby first time-series data consisting of the aggregated results of the daily expenditure of the medical insurance fund in chronological order may be obtained. In practice, the first time-series data may alternatively be time-series data in which the independent variable is expense time and the dependent variable is expense. Of course, the first time-series data may be time-series data in which the independent variable is expense cost and the dependent variable is expense time, and the like, and is not particularly limited herein.
S430, second time sequence data of medical insurance fund expenditure of the first subject before medical insurance treatment adjustment and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment are obtained.
It should be noted that the process of acquiring the second time-series data and the process of acquiring the first time-series data may be the same or different, and are not specifically limited herein. Similarly, the third time series data is obtained in a similar manner, and will not be described herein again.
S440, performing dimension reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data.
S450, fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment adjustment.
According to the technical scheme of the embodiment of the invention, the expenditure expenses of the medical insurance fund of the first object subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment are summarized according to the preset time interval, wherein the expenditure expenses comprise expenditure time and expenditure expenses under the expenditure time, and the expenditure expenses under each expenditure time corresponding to the time interval in the expenditure particulars are summarized, so that first time sequence data with uniform specifications are obtained.
EXAMPLE five
Fig. 5 is a block diagram illustrating a configuration of a device for predicting medical insurance fund expenditure according to a fifth embodiment of the present invention, where the device is configured to execute the method for predicting medical insurance fund expenditure according to any of the embodiments. The device and the medical insurance fund expenditure prediction method of each embodiment belong to the same inventive concept, and details which are not described in detail in the embodiment of the medical insurance fund expenditure prediction device can refer to the embodiment of the medical insurance fund expenditure prediction method. Referring to fig. 5, the apparatus may specifically include: a time series data acquisition module 510, a time series data processing module 520 and a medical insurance fund expenditure prediction module 530.
The time sequence data acquiring module 510 is configured to acquire first time sequence data of medical insurance fund expenditure of the first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of the first subject before medical insurance treatment adjustment, and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment;
the time sequence data processing module 520 is configured to perform dimension reduction on the first time sequence data according to the second time sequence data to obtain treatment feature sequence data generated based on medical insurance treatment adjustment, and predict fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and a medical insurance fund expenditure prediction module 530, configured to fuse the treatment feature sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object at a target time within a preset time period after the medical insurance treatment is adjusted.
Optionally, the time-series data processing module 520 may specifically include:
and the time series data dimension reduction unit is used for obtaining seasonal feature series data generated based on seasonal variation according to the second time series data and reducing dimension of the first time series data based on the seasonal feature series data.
On this basis, optionally, the dimension reduction unit of the time series data may specifically include:
a seasonal feature data determination subunit, configured to determine, for each piece of to-be-reduced dimensional data in the first time series data, seasonal feature data corresponding to the to-be-reduced dimensional data from the seasonal feature series data;
the dimensionality reduced data obtaining subunit is used for subtracting the seasonal characteristic data from the dimensionality data to be reduced to obtain dimensionality reduced data;
accordingly, the time-series data processing module 520 may further include:
and the treatment characteristic sequence data obtaining unit is used for taking sequence data formed by the reduced dimension data corresponding to each piece of dimension data to be reduced as treatment characteristic sequence data generated based on medical insurance treatment adjustment.
Optionally, the medical insurance fund expenditure prediction module 530 may specifically include:
and the sequence data superposition unit is used for superposing the characteristic sequence data to be processed on the fourth time sequence data.
On this basis, optionally, the sequence data superposition unit may specifically include:
a processing feature data determining subunit, configured to determine, for each to-be-superimposed data in the fourth time series data, processing feature data corresponding to the to-be-superimposed data from the to-be-superimposed feature sequence data;
the superposed data obtaining subunit is used for superposing the characteristic data to be superposed on the data to be superposed to obtain superposed data;
accordingly, the medical insurance fund expenditure prediction module 530 may further include:
and the medical insurance fund expenditure obtaining unit is used for obtaining the medical insurance fund expenditure of the second object at the target time within the preset time period after the medical insurance treatment is adjusted according to the sequence data formed by the superposed data corresponding to the data to be superposed respectively.
Optionally, the time-series data obtaining module 510 may include:
the expense detail acquiring unit is used for acquiring the expense detail of the medical insurance fund expense of the first object which is subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, wherein the expense detail comprises expense time and expense under the expense time;
and the first time sequence data obtaining unit is used for summarizing expenditure expenses at each expenditure time corresponding to the time interval in the expenditure details according to the preset time interval to obtain first time sequence data.
On this basis, optionally, the first time-series data includes sequence data in which the independent variable is a payout time and the dependent variable is a payout cost.
According to the medical insurance fund expenditure prediction device provided by the fifth embodiment of the invention, through the mutual cooperation of the time sequence data acquisition module and the time sequence data processing module, the dimension reduction is carried out on the first time sequence data of the medical insurance fund expenditure of the first object after the medical insurance treatment adjustment according to the acquired second time sequence data of the medical insurance fund expenditure of the first object subjected to the medical insurance treatment adjustment before the medical insurance treatment adjustment, so that the treatment characteristic sequence data which can show the influence on the medical insurance fund expenditure of the first object due to the medical insurance treatment adjustment can be obtained, and the fourth time sequence data of the medical insurance fund expenditure of the second object not subjected to the medical insurance treatment adjustment in the preset time period can be predicted according to the acquired third time sequence data of the medical insurance fund expenditure of the second object to be subjected to the medical insurance treatment adjustment; and then the medical insurance fund expenditure prediction module fuses the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after the medical insurance treatment is adjusted. According to the device, the treatment characteristic sequence data extracted from the time sequence data of the first object subjected to medical insurance treatment adjustment and generated due to medical insurance treatment adjustment is fused to the prediction result of medical insurance fund expenditure of the second object to be subjected to medical insurance treatment adjustment when medical insurance treatment adjustment is not carried out, so that the medical insurance fund expenditure of the second object after medical insurance treatment adjustment is obtained, and the effect of accurately predicting the medical insurance fund expenditure after medical insurance treatment adjustment is achieved.
The device for predicting medical insurance fund expenditure provided by the embodiment of the invention can execute the method for predicting medical insurance fund expenditure provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that, in the embodiment of the device for predicting medical insurance fund expenditure, the units and modules included in the device are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
EXAMPLE six
Fig. 6 is a schematic structural diagram of a device for predicting medical insurance fund expenditure according to a sixth embodiment of the present invention, and as shown in fig. 6, the device for predicting medical insurance fund expenditure includes a memory 610, a processor 620, an input device 630, and an output device 640. The number of processors 620 in the device for predicting medical insurance fund expenditure may be one or more, and one processor 620 is taken as an example in fig. 6; the memory 610, the processor 620, the input device 630 and the output device 640 of the medical insurance fund expenditure prediction apparatus may be connected by a bus or other means, and are exemplified by being connected by a bus 650 in fig. 6.
The memory 610 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for predicting medical insurance fund expenditure in the embodiment of the present invention (for example, the time-series data acquisition module 510, the time-series data processing module 520, and the medical insurance fund expenditure prediction module 530 in the device for predicting medical insurance fund expenditure). The processor 620 executes various functional applications and data processing of the medical insurance fund expenditure prediction apparatus by executing software programs, instructions and modules stored in the memory 610, that is, the medical insurance fund expenditure prediction method is implemented.
The memory 610 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 for at least one function; the storage data area may store data created from use of the prediction apparatus for medical insurance fund expenditure, and the like. Further, the memory 610 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 non-volatile solid state storage device. In some examples, memory 610 may further include memory located remotely from processor 620, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 630 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the device. The output device 640 may include a display device such as a display screen.
EXAMPLE seven
A seventh embodiment of the present invention provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for predicting medical insurance fund expenditure, the method comprising:
acquiring first time sequence data of medical insurance fund expenditure of a first subject subjected to medical insurance treatment adjustment after medical insurance treatment adjustment, second time sequence data of medical insurance fund expenditure of a second subject subjected to medical insurance treatment adjustment before medical insurance treatment adjustment and third time sequence data of medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment;
performing dimensionality reduction on the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and fusing the treatment characteristic sequence data and the fourth time sequence data to obtain medical insurance fund expenditure of the second object in the target time within the preset time period after medical insurance treatment is adjusted.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the method for predicting medical insurance fund expenditure provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. With this understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for predicting medical insurance fund expenditure is characterized by comprising the following steps:
acquiring first time sequence data of medical insurance fund expenditure of a first subject subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, second time sequence data of the medical insurance fund expenditure of a second subject subjected to medical insurance treatment adjustment before the medical insurance treatment adjustment and third time sequence data of the medical insurance fund expenditure of the second subject to be subjected to medical insurance treatment adjustment;
performing dimension reduction on the first time sequence data according to the second time sequence data to obtain treatment feature sequence data generated based on medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and fusing the treatment characteristic sequence data and the fourth time sequence data to obtain the medical insurance fund expenditure of the second object in the target time within the preset time period after the medical insurance treatment is adjusted.
2. The method of claim 1, wherein the dimension reduction of the first time series data according to the second time series data comprises:
seasonal feature sequence data generated based on seasonal variation is obtained according to the second time sequence data, and dimension reduction is carried out on the first time sequence data based on the seasonal feature sequence data.
3. The method of claim 2, wherein the dimensionality reduction of the first time-series data based on the seasonal feature sequence data comprises:
for each dimension data to be reduced in the first time sequence data, determining seasonal feature data corresponding to the dimension data to be reduced from the seasonal feature sequence data;
subtracting the seasonal feature data from the dimension data to be reduced to obtain dimension-reduced data;
correspondingly, the obtaining of the treatment feature sequence data generated based on the medical insurance treatment adjustment includes:
and taking sequence data formed by the reduced dimension data corresponding to each dimension data to be reduced as treatment characteristic sequence data generated based on the medical insurance treatment adjustment.
4. The method of claim 1, wherein fusing the treatment feature sequence data and the fourth time sequence data comprises:
superimposing the treatment feature sequence data on the fourth time sequence data.
5. The method of claim 4, wherein the superimposing the encounter feature sequence data on the fourth time sequence data comprises:
for each data to be superposed in the fourth time series data, determining the characteristic data to be superposed corresponding to the data to be superposed from the characteristic sequence data to be encountered;
superposing the characteristic data to be superposed on the data to be superposed to obtain superposed data;
correspondingly, the obtaining of the medical insurance fund expenditure of the second object at the target time within the preset time period after the medical insurance treatment is adjusted includes:
and according to sequence data formed by the superposed data corresponding to the data to be superposed respectively, acquiring the medical insurance fund expenditure of the second object at the target time within the preset time period after the medical insurance treatment is adjusted.
6. The method of claim 1, wherein the obtaining medical insurance fund expenditure of the first subject having performed the medical insurance treatment adjustment first time-series data after the medical insurance treatment adjustment comprises:
acquiring a expenditure detail of medical insurance fund expenditure of a first object subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, wherein the expenditure detail comprises expenditure time and expenditure expense cost under the expenditure time;
and summarizing the expenditure expenses at each expenditure time corresponding to the time interval in the expenditure details according to a preset time interval to obtain first time series data.
7. The method of claim 6, wherein the first time-series data comprises sequence data in which an independent variable is the payout time and a dependent variable is the payout cost.
8. An apparatus for predicting medical insurance fund expenditure, comprising:
the time sequence data acquisition module is used for acquiring first time sequence data of medical insurance fund expenditure of a first subject subjected to medical insurance treatment adjustment after the medical insurance treatment adjustment, second time sequence data of the medical insurance fund expenditure of a second subject subjected to the medical insurance treatment adjustment before the medical insurance treatment adjustment and third time sequence data of the medical insurance fund expenditure of the second subject subjected to the medical insurance treatment adjustment;
the time sequence data processing module is used for reducing the dimension of the first time sequence data according to the second time sequence data to obtain treatment characteristic sequence data generated based on the medical insurance treatment adjustment, and predicting fourth time sequence data of medical insurance fund expenditure of the second object in a preset time period according to the third time sequence data;
and a medical insurance fund expenditure prediction module for fusing the treatment characteristic sequence data and the fourth time sequence data to obtain the medical insurance fund expenditure of the second object within the preset time period after the medical insurance treatment is adjusted.
9. An apparatus for predicting medical insurance fund expenditure, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of predicting medical insurance fund expenditure as defined in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of predicting medical insurance fund expenditure as set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110098229.3A CN112734585A (en) | 2021-01-25 | 2021-01-25 | Method, device, equipment and storage medium for predicting medical insurance fund expenditure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110098229.3A CN112734585A (en) | 2021-01-25 | 2021-01-25 | Method, device, equipment and storage medium for predicting medical insurance fund expenditure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112734585A true CN112734585A (en) | 2021-04-30 |
Family
ID=75595309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110098229.3A Pending CN112734585A (en) | 2021-01-25 | 2021-01-25 | Method, device, equipment and storage medium for predicting medical insurance fund expenditure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734585A (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130159023A1 (en) * | 2011-12-16 | 2013-06-20 | Neela SRINIVAS | System and method for evidence based differential analysis and incentives based heal thcare policy |
| CN103745424A (en) * | 2014-02-14 | 2014-04-23 | 上海市东方医院（同济大学附属东方医院） | Hospital comprehensive performance information processing system and method |
| US20140229233A1 (en) * | 2013-02-13 | 2014-08-14 | Mastercard International Incorporated | Consumer spending forecast system and method |
| CN105678538A (en) * | 2016-01-12 | 2016-06-15 | 山大地纬软件股份有限公司 | A health care settlement mobile payment method based on bluetooth beacons and a system of the method |
| CN106408408A (en) * | 2016-09-14 | 2017-02-15 | 济南浪潮高新科技投资发展有限公司 | Realization method of tax optimal calculation by enterprise annuity business system |
| CN108460693A (en) * | 2018-03-29 | 2018-08-28 | 平安健康保险股份有限公司 | Insure character surveillance method and device, storage medium and the terminal of chain hospital |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109492829A (en) * | 2018-12-13 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance fund expenditure prediction technique and relevant apparatus based on artificial intelligence |
| CN109711665A (en) * | 2018-11-20 | 2019-05-03 | 深圳壹账通智能科技有限公司 | A kind of prediction model construction method and relevant device based on financial air control data |
| CN109767038A (en) * | 2019-01-04 | 2019-05-17 | 平安科技（深圳）有限公司 | Crop yield prediction technique, device and computer readable storage medium |
| CN109785151A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of emulation mode and device of medical insurance policies |
| CN109785154A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | A kind of Risk Forecast Method and device based on intelligent decision |
| CN109948645A (en) * | 2019-01-23 | 2019-06-28 | 西安交通大学 | A kind of enterprise based on depth confrontation transfer learning evades the tax recognition methods |
| CN110210985A (en) * | 2019-05-31 | 2019-09-06 | 太平洋医疗健康管理有限公司 | Basic medical insurance policies adjust the quantization method influenced on fund expenditure and system |
| CN110223517A (en) * | 2019-06-20 | 2019-09-10 | 青岛科技大学 | Short-term traffic flow forecast method based on temporal correlation |
| CN111325576A (en) * | 2020-02-17 | 2020-06-23 | 卫宁健康科技集团股份有限公司 | Method and system for predicting cost of disease diagnosis related group and electronic equipment |
| CN111815052A (en) * | 2020-07-08 | 2020-10-23 | 泰康保险集团股份有限公司 | Medical expense data processing method and device |
-
2021
- 2021-01-25 CN CN202110098229.3A patent/CN112734585A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130159023A1 (en) * | 2011-12-16 | 2013-06-20 | Neela SRINIVAS | System and method for evidence based differential analysis and incentives based heal thcare policy |
| US20140229233A1 (en) * | 2013-02-13 | 2014-08-14 | Mastercard International Incorporated | Consumer spending forecast system and method |
| CN103745424A (en) * | 2014-02-14 | 2014-04-23 | 上海市东方医院（同济大学附属东方医院） | Hospital comprehensive performance information processing system and method |
| CN105678538A (en) * | 2016-01-12 | 2016-06-15 | 山大地纬软件股份有限公司 | A health care settlement mobile payment method based on bluetooth beacons and a system of the method |
| CN106408408A (en) * | 2016-09-14 | 2017-02-15 | 济南浪潮高新科技投资发展有限公司 | Realization method of tax optimal calculation by enterprise annuity business system |
| CN108460693A (en) * | 2018-03-29 | 2018-08-28 | 平安健康保险股份有限公司 | Insure character surveillance method and device, storage medium and the terminal of chain hospital |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109711665A (en) * | 2018-11-20 | 2019-05-03 | 深圳壹账通智能科技有限公司 | A kind of prediction model construction method and relevant device based on financial air control data |
| CN109492829A (en) * | 2018-12-13 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance fund expenditure prediction technique and relevant apparatus based on artificial intelligence |
| CN109785151A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of emulation mode and device of medical insurance policies |
| CN109785154A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | A kind of Risk Forecast Method and device based on intelligent decision |
| CN109767038A (en) * | 2019-01-04 | 2019-05-17 | 平安科技（深圳）有限公司 | Crop yield prediction technique, device and computer readable storage medium |
| CN109948645A (en) * | 2019-01-23 | 2019-06-28 | 西安交通大学 | A kind of enterprise based on depth confrontation transfer learning evades the tax recognition methods |
| CN110210985A (en) * | 2019-05-31 | 2019-09-06 | 太平洋医疗健康管理有限公司 | Basic medical insurance policies adjust the quantization method influenced on fund expenditure and system |
| CN110223517A (en) * | 2019-06-20 | 2019-09-10 | 青岛科技大学 | Short-term traffic flow forecast method based on temporal correlation |
| CN111325576A (en) * | 2020-02-17 | 2020-06-23 | 卫宁健康科技集团股份有限公司 | Method and system for predicting cost of disease diagnosis related group and electronic equipment |
| CN111815052A (en) * | 2020-07-08 | 2020-10-23 | 泰康保险集团股份有限公司 | Medical expense data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019056681A1 (en) | Real-time data monitoring method, device, terminal apparatus, and storage medium | |
| US20140006044A1 (en) | System and method for preparing healthcare service bundles | |
| CN104811344A (en) | Network dynamic service monitoring method and apparatus | |
| CN109472608A (en) | Business confirmation method and terminal device based on Emotion identification | |
| CN109697667B (en) | Quota management and control method and device based on trust mode | |
| CN107784504A (en) | Client pays a return visit the generation method and terminal device of event | |
| CN111428978A (en) | Subsidy calculation method and device, electronic equipment and storage medium | |
| CN110751549A (en) | Management and control method and device for overdue financial loan collection and acceptance promotion and electronic equipment | |
| CN109118349A (en) | Business finance bill generation method, device, electronic equipment and storage medium | |
| WO2020082807A1 (en) | Medical insurance fund risk control method and device based on data analysis, server, and medium | |
| CN105405051B (en) | Financial event prediction method and device | |
| CN111815052B (en) | Medical expense data processing method and device | |
| CN113052684A (en) | Risk prediction method of financial product, related device and computer storage medium | |
| CN112734585A (en) | Method, device, equipment and storage medium for predicting medical insurance fund expenditure | |
| CN113537631B (en) | Medicine demand prediction method, device, electronic equipment and storage medium | |
| CN114298847A (en) | Prediction method, device, equipment and storage medium for employee medical insurance fund balance | |
| CN115271929A (en) | Data anomaly detection method, device, equipment, medium and program product | |
| CN111199799A (en) | Health prompt information processing method and device and terminal equipment | |
| CN110766556A (en) | Profit notification method, device, equipment and computer readable storage medium | |
| CN105868217A (en) | Automatic conversion method and system for numerical value | |
| CN114647555B (en) | Data early warning method, device, equipment and medium based on multi-service system | |
| CN111967966B (en) | Automatic wake-up method and system for sleep clients of mobile phone banks | |
| US11544753B2 (en) | Indicating forecasts of invoice payments | |
| CN113743532B (en) | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and computer storage medium | |
| KR102148152B1 (en) | Processing method and apparatus for financial instrument information |
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 |