Drug data treatment method and system based on price conversion

Abstract

The invention belongs to the field of data management, and provides a drug data management method and system based on price conversion, and the method comprises the steps: obtaining medical insurance drug cost detail data, carrying out the data cleaning, and carrying out the mapping with a medical insurance drug directory, and forming to-be-analyzed drug data; generating a drug data classification standard according to the to-be-analyzed drug data; setting data groups and classification rules according to drug data classification standards, classifying the cleaned medical insurance drug cost detail data according to the classification rules and sales unit prices and sales quantities in the cleaned medical insurance drug cost detail data, and putting the classified medical insurance drug cost detail data into corresponding data groups; performing management according to different data groups, uniformly converting the data into minimum packaging prices, and marking data which cannot be converted as deviated normal data; and further identifying and processing the data deviating from normal data, and identifying the data which are uploaded abnormally at high price and the data which are uploaded abnormally. And the accuracy and efficiency of drug price monitoring are improved.

Description

Technical Field

[0001] The present invention belongs to the field of data governance technology, and specifically relates to a drug data governance method and system based on price conversion. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Medical insurance drug data is primarily used for applications such as price monitoring and drug supply analysis. However, current drug data suffers from quality issues, hindering its effective application. The primary issue is inconsistent drug price units. Conventionally, drug unit prices may be expressed in terms of the smallest packaging unit, the smallest dosage unit, or even smaller units. Inconsistent drug price units have significant impacts on data analysis. First, data comparability is reduced, making horizontal and vertical comparisons impossible. Second, drug price regulation becomes more difficult and complex. Third, it impacts the construction of drug price indices, which require a unified price unit to ensure data accuracy and representativeness. Fourth, data integration and sharing are difficult. The main reasons for inconsistent drug price units are: first, drug data comes from multiple sources, such as hospitals and pharmacies, and these sources have different data formats and price units. Second, there is a lack of a unified, standardized interface for drug data collection, resulting in inconsistent data formats across different sources. Third, there is a lack of price unit verification mechanisms during data storage, leading to incorrect or inconsistent data entering the system. Fourth, existing data analysis tools are insufficiently capable of processing non-standardized data and are unable to effectively identify and process data with different price units.

[0004] Therefore, a method for drug data governance is needed to solve the problem of inconsistent drug price units, thereby effectively reducing the impact of inconsistent drug price units on data analysis and improving the accuracy and efficiency of drug price monitoring. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes a drug data governance method and system based on price conversion. The present invention integrates drug data with medical insurance catalog data, constructs a drug data classification standard, completes data grouping according to fixed grouping rules, performs price conversion on drug grouped data, and further processes the data that cannot be converted using an outlier processing method.

[0006] According to some embodiments, a first solution of the present invention provides a drug data governance method based on price conversion, which adopts the following technical solutions: A drug data governance method based on price conversion, including: Obtain detailed data on medical insurance drug costs, clean the data, and then map it with the medical insurance drug catalog to generate drug data to be analyzed; Generate drug data classification standards based on the drug data to be analyzed; Set data grouping and classification rules according to the drug data classification standards. Classify the cleaned medical insurance drug expense details data based on the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data and include them in the corresponding data groupings. The cleaned medical insurance drug expense details are managed according to different data groups and uniformly converted to the minimum package price. Data that cannot be converted is marked as deviating from normal data. Further identify and process data that deviates from the normal state, and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0007] Furthermore, the detailed data of medical insurance drug costs is obtained and mapped with the medical insurance drug catalog after data cleaning to form the drug data to be analyzed, specifically: Obtain detailed data on medical insurance drug costs, including drug medical insurance catalog code, drug name, sales quantity, and sales unit price; Perform data cleaning on the acquired medical insurance drug expense details data to obtain cleaned medical insurance drug expense details data; Based on the cleaned medical insurance drug cost details data, it is mapped with the medical insurance drug catalog to obtain the corresponding medical insurance drug catalog data; among them, the medical insurance drug catalog data includes the medical insurance catalog code, medical insurance catalog name, minimum packaging quantity, whether it is listed online, and the online price.

[0008] Furthermore, the drug data classification standard is generated based on the drug data to be analyzed, specifically: The drug data classification standards include drug unit price classification standards, drug quantity classification standards and unit price classification standard thresholds; Calculate the drug unit price classification standard based on the sales unit price in the medical insurance drug sales expense details and the corresponding drug catalog data; Calculate the drug quantity classification standard based on the sales quantity of the medical insurance drug sales expense details and the corresponding drug catalog data; The unit price classification standard threshold is calculated based on the sales unit price and drug unit price classification standard in the medical insurance drug sales expense details.

[0009] Furthermore, the data grouping and classification rules are set according to the drug data classification standard, and the cleaned medical insurance drug expense details data are classified according to the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data, specifically: Set data groups, including data sets uploaded according to the minimum packaging unit as Group A, data sets uploaded according to the minimum preparation unit as Group B, data sets uploaded according to less than the minimum preparation unit as Group C, and data sets deviating from the normal range as Group D; If the sales unit price distribution is within the unit price classification standard threshold range, it will be included in data group A; If the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard = minimum package quantity, then: if the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, it will be included in data group B; if the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, it deviates from the normal range and is included in data group D; If the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard ≠ minimum package quantity, then: If the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, but the sales unit price * drug quantity classification standard distribution is outside the unit price classification standard threshold range, it will be included in data group B; If the sales unit price * drug quantity classification standard distribution is within the unit price classification standard threshold range, but the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, the data will be included in group C; If the sales unit price * quantity classification standard and the sales unit price * minimum package quantity are both distributed within the unit price classification standard threshold range, then: if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, and the sales quantity can be divided evenly by the quantity classification standard, it is included in data group C; if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, the sales quantity cannot be divided evenly by the quantity classification standard, but the sales quantity can be divided evenly by the minimum package quantity, it is included in data group B; if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, the sales quantity cannot be divided evenly by the quantity classification standard, and the sales quantity If the quantity cannot be divided evenly into the minimum package quantity, it shall be included in data group C; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, and the sales quantity can be divided evenly into the minimum package quantity, it shall be included in data group B; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, the sales quantity cannot be divided evenly into the minimum package quantity, but the sales quantity can be divided evenly into the quantity classification standard, it shall be included in data group C; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, the sales quantity cannot be divided evenly into the minimum package quantity, and the sales quantity cannot be divided evenly into the quantity classification standard, it shall be included in data group B; If the sales unit price*quantity classification standard and the sales unit price*minimum package quantity are both distributed within and outside the unit price classification standard threshold range, they are included in data grouping group D.

[0010] Furthermore, the cleaned medical insurance drug expense details data are managed according to different data groups and uniformly converted to the minimum package price. Data that cannot be converted is marked as deviating from normal data, specifically: Group A data is the cleaned medical insurance drug expense details data uploaded according to the normal packaging unit. The management sales price = sales unit price, and the management sales quantity = sales quantity. Group B data belongs to the cleaned medical insurance drug cost details data uploaded according to the minimum dosage unit. The management sales price = sales unit price * sales quantity, and the management sales quantity = sales quantity / minimum packaging quantity; Group C data belongs to the cleaned medical insurance drug cost details data uploaded based on units smaller than the minimum dosage unit. The management sales price = sales unit price * quantity classification standard, and the management sales quantity = sales quantity / quantity classification standard; The data group D belongs to the medical insurance drug cost details data after cleaning that deviates from the normal value and is marked as deviating from the normal data.

[0011] Furthermore, the further identification and processing of data that deviates from the normal state, identifying data uploaded at abnormally high prices and data uploaded with abnormal data, is specifically as follows: Conduct normality tests on the sales unit prices of the same type of drugs in data that deviate from the normal distribution. For data that follow a normal distribution or approximately follow a normal distribution, use the 3σ principle to identify data uploaded with abnormally high prices and data with abnormalities. For data that deviates from normal distribution and does not follow the normal distribution, the box plot outlier processing method is used to identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0012] According to some embodiments, a second solution of the present invention provides a drug data governance system based on price conversion, which adopts the following technical solutions: A drug data governance system based on price conversion, including: The data docking and processing module is used to obtain detailed data on medical insurance drug costs, and after data cleaning, it is mapped with the medical insurance drug catalog to achieve data fusion and form the drug data to be analyzed; The drug price conversion module is used to formulate drug data classification standards, group the cleaned medical insurance drug cost details data, and realize drug price conversion. It cannot convert data that deviates from normal. The abnormal data processing module is used to further process data that deviates from normal data and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0013] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0014] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a drug data governance method based on price conversion as described in the first aspect above.

[0015] According to some embodiments, a fourth aspect of the present invention provides a computer device.

[0016] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a drug data governance method based on price conversion as described in the first aspect above are implemented.

[0017] According to a fifth aspect of the present invention, there is provided a computer program product or computer program according to some embodiments.

[0018] The present invention provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the drug data governance method based on price conversion as described in the first aspect above.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention constructs a data governance method and device based on price conversion, which governs drug data from different sources, and uniformly converts drug unit price data and quantity data expressed in the form of minimum packaging unit, minimum preparation unit or less than the minimum preparation unit into prices and quantities of the same unit, so as to facilitate the subsequent development of various drug data analysis applications, and at the same time screen out abnormal data that deviates from normal values ​​and clear dirty data, effectively improving the quality of drug data.

[0020] The present invention constructs a data governance method based on price conversion, which uniformly organizes and cleans the detailed sales data of designated drugs, maps the detailed drug data with the medical insurance catalog data, and uses the minimum packaging quantity, online price and other data of the medical insurance catalog data standard to convert the drug price data according to the national unified standard, thereby improving the standardization of data conversion.

[0021] The present invention constructs a data governance method based on price conversion. By constructing a drug classification standard, the classification standard is constructed by taking the minimum value greater than or equal to the mean of the unit price and quantity of non-listed drugs. The unit price classification standard threshold is calculated based on the classification standard to reduce the calculation deviation caused by different pricing units. At the same time, the inconsistency of actual sales prices of different medical institutions is taken into account to enhance the accuracy of data classification.

[0022] The present invention constructs a data governance method based on price conversion. According to the data classification standard, refined data classification rules are formulated to divide the target data into four groups, so as to achieve accurate classification of data with different pricing units. Different groups are governed in different ways, and each group of data is uniformly converted into the "minimum packaging" unit pricing. The data can be used for drug data analysis applications such as drug price comparison, drug price supervision, drug price index construction, and drug market analysis to improve the accuracy of the analysis.

[0023] This data governance method, based on price conversion, identifies abnormal data that deviates from normal values. This data can be included in subsequent key governance areas and can also serve as key analysis data for drug anomaly supervision. Furthermore, for abnormal data that deviates from normal values, the 3σ principle and boxplot outlier detection methods are used to identify obvious dirty data and classify it for processing, thereby improving data processing capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0025] Figure 1 This is a flowchart of a method for managing drug data based on price conversion according to an embodiment of the present invention; Figure 2 This is an architecture diagram of a drug data governance system based on price conversion in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0027] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0028] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0029] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0030] Example 1 This embodiment provides a drug data governance method based on price conversion. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal, a server, and a server, and is implemented through the interaction between the terminal and the server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communications, middleware services, domain name services, security services CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected by wired or wireless communication, which is not limited in this application. In this embodiment, the method includes the following steps: Obtain detailed data on medical insurance drug costs, clean the data, and then map it with the medical insurance drug catalog to generate drug data to be analyzed; Generate drug data classification standards based on the drug data to be analyzed; Set data grouping and classification rules according to the drug data classification standards. Classify the cleaned medical insurance drug expense details data based on the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data and include them in the corresponding data groupings. The cleaned medical insurance drug expense details are managed according to different data groups and uniformly converted to the minimum package price. Data that cannot be converted is marked as deviating from normal data. Further identify and process data that deviates from the normal state, and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0031] The specific steps of this embodiment include the following: Step 1: Obtain detailed data on medical insurance drug costs, clean the data, and then map it with the medical insurance drug catalog to form the drug data to be analyzed; Step 2: Generate drug data classification standards based on the drug data to be analyzed, including drug unit price classification standards, drug quantity classification standards, and unit price classification standard thresholds; Step 3: Set data grouping and classification rules according to the drug data classification standard. Classify the cleaned medical insurance drug expense details data according to the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data and place them into the corresponding data grouping; Step 4: Manage the cleaned medical insurance drug cost details data according to different data groups, uniformly convert them to the minimum package price, and mark those that cannot be converted as deviating from normal data; Step 5: Use the 3σ principle and boxplot outlier detection method to further identify and process data that deviates from the normal state, and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0032] like Figure 1 As shown, as an embodiment, a specific implementation process of a drug data governance method based on price conversion is as follows: Step 1: Obtain detailed data on medical insurance drug costs, map the cleaned detailed data on medical insurance drug costs with the medical insurance drug catalog, achieve data fusion, and form drug data to be analyzed.

[0033] Step 1-1, obtain detailed data on medical insurance drug costs, which should at least include key information such as the drug medical insurance catalog code, drug name, sales quantity, and sales unit price.

[0034] Step 1-2: clean the acquired medical insurance drug expense details data, remove abnormal data with sales unit price less than or equal to 0, sales quantity less than or equal to 0, and corresponding missing data, and obtain the cleaned medical insurance drug expense details data.

[0035] Steps 1-3: Based on the cleaned medical insurance drug cost details data, map it with the medical insurance drug catalog to obtain the corresponding medical insurance drug catalog data; among them, the medical insurance drug catalog data includes the medical insurance catalog code, medical insurance catalog name, minimum packaging quantity, whether it is listed online, and the online price of the drug. The medical insurance cost details data and the medical insurance drug catalog data are integrated to form the drug data to be analyzed.

[0036] Step 2: Generate drug data classification standards based on the drug data to be analyzed. The generation of drug data classification standards is divided into three parts, including drug unit price classification standards, drug quantity classification standards, and unit price classification standard thresholds.

[0037] Step 2-1: Calculate the drug unit price classification standard P based on the sales unit price in the medical insurance drug sales expense details and the corresponding drug catalog data.

[0038] In step 2-1-1, when the drug is a listed drug, the drug unit price classification standard is the listed price in the drug catalog data; In step 2-1-2, if the drug is not listed online, calculate the different sales unit values ​​based on the sales unit price of the same medical insurance catalog code. Duplicate sales unit prices are only taken once. Calculate the average of the different sales unit prices of the same drug (same medical insurance catalog code). The minimum value greater than or equal to the average is used as the drug unit price classification standard. Step 2-2, calculate the drug quantity classification standard M based on the sales quantity of the medical insurance drug sales expense details and the corresponding drug catalog data.

[0039] Based on the sales quantity of the same medical insurance catalog code, calculate the different sales quantity values, where repeated sales quantity is only taken once, and find the average of the different sales quantities of the same drug (same medical insurance catalog code). The minimum value greater than or equal to the average is used as the drug quantity classification standard; Step 2-3: Calculate the unit price classification threshold (P) based on the sales unit price of the drug reagent and the drug unit price classification standard P. min ,P max ); In step 2-3-1, specifically, the unit price classification standard index of the drug is used as the benchmark value for determining the threshold, and the acceptable deviation degree of the benchmark value is calculated using the drug cost detail data, which is used as the benchmark value fluctuation coefficient, thereby obtaining the unit price classification standard threshold.

[0040] Furthermore, when calculating the baseline fluctuation coefficient, the formula is used: Standard Deviation = (1); Baseline value fluctuation coefficient = standard deviation / drug unit price classification standard (2); Among them, the standard deviation can accurately measure the degree of dispersion of the data and reflect the degree of deviation between the sales unit price and the unit price classification standard in the medical insurance drug sales expense details.

[0041] Using formulas (1) and (2), it can be concluded that the larger the benchmark value fluctuation coefficient, the more data deviates from the unit price classification standard, and the degree of deviation is larger. There are more price data uploaded according to different units in the data, and the data quality is poor. The smaller the benchmark value fluctuation coefficient, the fewer data deviates from the unit price classification standard, and the degree of deviation is smaller. There are fewer price data uploaded according to different units in the data, and the data quality is better.

[0042] In step 2-3-2, after obtaining the baseline fluctuation coefficient, calculate the relative threshold of the unit price classification standard. Based on the degree of deviation between the sales unit price in the medical insurance drug sales expense details and the unit price classification standard as reflected by the baseline fluctuation coefficient, the calculation is divided into two cases: Case 1: If the baseline fluctuation coefficient is greater than or equal to 0.5, the relative threshold range of the unit price classification standard is: Pmin= (3); Pmax= (4); Case 2: If the benchmark value fluctuation coefficient is less than 0.5, the relative threshold range of the unit price classification standard is: Pmin= (5); Pmax= (6); Step 3: Set data grouping and classification rules. Classify the cleaned medical insurance drug expense details data according to the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data and include them in the corresponding data groups.

[0043] Step 3-1, set data grouping. Specifically, the data set uploaded according to the minimum packaging unit is Group A, the data set uploaded according to the minimum preparation unit is Group B, the data set uploaded according to less than the minimum preparation unit is Group C, and the data set deviating from the normal range is Group D.

[0044] The classification rules mainly include: In step 3-2, if the sales unit price distribution is within the unit price classification standard threshold range, then it is included in data group A; In step 3-3, if the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard = minimum package quantity, then: Step 3-3-1: If the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, then include it in data group B; In step 3-3-2, if the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, then include it in data group D; In step 3-4, if the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard ≠ minimum package quantity, then: In step 3-4-1, if the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, but the sales unit price * drug quantity classification standard distribution is outside the unit price classification standard threshold range, then upload according to the minimum dosage unit and include it in data group B; In step 3-4-2, if the sales unit price * drug quantity classification standard distribution is within the unit price classification standard threshold range, but the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, then upload it as less than the minimum dosage unit and include it in data group C; In step 3-4-3, if both sales unit price * quantity classification standard and sales unit price * minimum package quantity are within the unit price classification standard threshold range, then: In step 3-4-3-1, if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, and the sales quantity can divide the quantity classification standard, then upload it as less than the minimum dosage unit and include it in data group C; In step 3-4-3-2, if the difference between sales unit price * drug quantity classification standard and drug unit price classification standard is less than the difference between sales unit price * minimum package quantity and drug unit price classification standard, and the sales quantity cannot divide the quantity classification standard, but the sales quantity can divide the minimum package quantity, then upload according to the minimum dosage unit and include it in data group B; In step 3-4-3-3, if the difference between sales unit price * drug quantity classification standard and drug unit price classification standard is less than the difference between sales unit price * minimum package quantity and drug unit price classification standard, and the sales quantity cannot divide the quantity classification standard, and the sales quantity cannot divide the minimum package quantity, then upload it as less than the minimum dosage unit and include it in data group C; In step 3-4-3-4, if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, and the sales quantity can be divided evenly by the minimum package quantity, then upload according to the minimum dosage unit and include it in data group B; In step 3-4-3-5, if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, and the sales quantity cannot divide the minimum package quantity, but the sales quantity can divide the quantity classification standard, then upload it as less than the minimum dosage unit and include it in data group C; In step 3-4-3-6, if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, and the sales quantity cannot be divided evenly by the minimum package quantity, and the sales quantity cannot be divided evenly by the quantity classification standard, then upload according to the minimum dosage unit and include it in data group B; In step 3-4-4, if both sales unit price * quantity classification standard and sales unit price * minimum package quantity are both within and outside the unit price classification standard threshold range, the cleaned medical insurance drug expense details data deviates from the normal range and is included in data group D; It is understandable that the objects of the above classification are all cleaned medical insurance drug cost details data, and an entire cleaned medical insurance drug cost details data is included in the data grouping.

[0045] To further describe the data classification standard, the classification steps in step 3 are classified according to the method shown in Table 1: Table 1 Data classification standard diagram

[0046] Step 4: After grouping, different groups are governed in different ways. The data of groups ABC are uniformly converted into the minimum packaging unit for pricing, and the data of group D that cannot be converted is marked as deviating from normal data. Specifically: Group A data is the cleaned medical insurance drug expense details data uploaded according to the normal packaging unit. The management sales price = sales unit price, and the management sales quantity = sales quantity. Group B data belongs to the cleaned medical insurance drug cost details data uploaded according to the minimum dosage unit. The management sales price = sales unit price * sales quantity, and the management sales quantity = sales quantity / minimum packaging quantity; Group C data belongs to the cleaned medical insurance drug cost details data uploaded according to smaller dosage units. The management sales price = sales unit price * quantity classification standard, and the management sales quantity = sales quantity / quantity classification standard; The data grouping in group D belongs to the detailed data of medical insurance drug expenses that have been cleaned and deviate from the normal values. It is marked as deviating data from the normal values ​​and can be used as key data for data anomaly analysis. When conducting refined analysis, it can also be identified as dirty data and excluded according to its own needs, thereby improving data quality and enhancing data practicality.

[0047] Obtain the governance sales price and governance sales quantity of groups A, B, and C, and include them in the post-governance dataset. Step 5: After grouping and governance, further identify the data in Group D and use the 3σ principle and boxplot outlier detection method to identify dirty data such as data uploaded at abnormally high prices and data uploaded with abnormal data.

[0048] Step 5-1: Perform a normality test on the sales price data of the same type of drugs in Group D. Use the 3σ principle to identify abnormally high-priced uploaded data and abnormal uploaded data for the normal distribution data in Group D that deviate from the normal distribution.

[0049] Step 5-1-1, perform a normality test on the data that deviates from the normal range, that is, perform a normality test on the sales unit prices of the same type of drugs in group D data (the data set that deviates from the normal range) to check whether they obey the normal distribution or approximate the normal distribution.

[0050] Specifically, for sales with the same medical insurance catalog code, calculate the overall descriptive statistics of the sales unit price, and use the KS test to determine whether the overall presentation level of the sales unit price is significant (P < 0.05): If the significance level P>0.05, the deviated normal data are considered to follow the normal distribution; If the significance level P<0.05, it is considered that the data deviates from the normal distribution and does not meet the absolute normal distribution. Other auxiliary indicators are needed to verify whether the data approximately obey the normal distribution.

[0051] Furthermore, based on the statistical indicators kurtosis and skewness, we further analyze whether the data deviating from normality approximately obey the normal distribution: if the absolute value of kurtosis is less than 10 and the absolute value of skewness is less than 3, then the data deviating from normality approximately obey the normal distribution; if the absolute value of kurtosis is not less than 10 and the absolute value of skewness is less than 3, then the data deviating from normality does not obey the normal distribution.

[0052] In step 5-1-2, if the data obeys the normal distribution or approximates the normal distribution, the 3σ principle outlier processing method is used to calculate the threshold interval (μ-3σ, μ+3σ), and the data that deviates from the normal outside the threshold is processed. If the unit price is greater than μ+3σ, it is determined to be an abnormal price, indicating that the deviation from the normal data is sold at a price higher than the reasonable price range. The data is identified and marked as abnormally high-priced uploaded data. If the sales unit price is less than μ-3σ, identify and mark the data that deviates from the normal state as data anomaly and upload the data.

[0053] In step 5-2, if the data does not obey the normal distribution, the box plot outlier processing method is used to identify abnormally high-priced uploaded data and abnormal uploaded data in the data set that deviates from the normal range.

[0054] In step 5-2-1, arrange the sales unit prices in ascending order, calculate the positions of the quartiles, including the first quartile (Q1), the second quartile (Q2), and the third quartile (Q3), and determine the quartile values ​​based on the positions. In step 5-2-2, the interquartile range (IQR) is calculated, and the maximum and minimum estimated values ​​are determined based on the IQR to determine the outlier boundaries.

[0055] Specifically, IQR = Q3 - Q1 If IQR = 0: Minimum estimated value = (1-baseline value fluctuation coefficient) * Q1 Maximum estimated value = (1 + baseline value fluctuation coefficient)*Q3 If IQR>0: Minimum estimate: Q1 - (1 + baseline fluctuation coefficient)*IQR Maximum estimate: Q3 + (1 + baseline fluctuation coefficient)*IQR In step 5-2-3, if the sales price is higher than the maximum estimated value, the data that deviates from the normal state is abnormally uploaded at a high price; if the sales price is lower than the minimum estimated value, the data that deviates from the normal state is abnormally uploaded data.

[0056] Identify outliers. All data points above the upper bound or below the lower bound are considered outliers. Outliers can be deleted, truncated, or retained based on business needs.

[0057] Based on a specific example, in order to more clearly illustrate the formulation of drug data classification standards, data grouping and conversion process of the present invention, the processing steps in the method are explained.

[0058] Step 1: Integrate and map the detailed drug consumption data of designated medical institutions and the medical insurance drug catalog data to form the drug data to be analyzed, including sales unit price, sales quantity, whether it is listed online, etc. The specific data content is shown in Table 2: Table 2 Integration and mapping relationship between drug consumption details data and medical insurance drug catalog data

[0059] The drug codes uniformly use the medical insurance drug catalog codes, the sales unit price and sales quantity come from the drug sales details of medical institutions, the minimum packaging quantity and whether it is posted online come from the medical insurance drug catalog, and the number of sales is the number of times the sales records with the same drug code, the same sales unit price and the same sales quantity appear. The records are merged for easy observation.

[0060] Step 2: Determine the data classification standard and calculate the drug unit price classification standard, drug quantity classification standard, and unit price classification standard threshold. At this time, ignore the impact of sales times on the classification standard results, as shown in Table 3.

[0061] Table 3 Calculation results of drug data classification standards

[0062] Take the drug XN02BED158A001010205889 as an example: Calculate the average sales price = (1 + 1.2 + 16 + 0.1 + 32) / 5 = 10.06; The classification standard for drug unit price is the minimum value greater than or equal to the mean, which is 16.

[0063] Calculate the mean sales quantity = (16 + 32 + 1 + 5 + 2) / 5 = 11.2; The classification standard for drug quantity is the minimum value greater than or equal to the mean, which is 16; Drug standard deviation = =9.746 Benchmark volatility coefficient = standard deviation / unit price classification standard = 9.746 / 16 = 0.609 The threshold range of the unit price classification standard is: Pmin= =9 Pmax= =26 Step 3: After determining the data classification criteria, classify the data into groups according to the specific classification rules. The specific execution steps are shown in Table 4: Table 4 Data classification and grouping results

[0064] Take the drug XN02BED158A001010205889 as an example: Take the first row as an example: the drug sales unit price of 1 is outside the unit price classification standard threshold, but the sales unit price * minimum package quantity is within the unit price classification standard threshold. This part of the data is considered to be uploaded based on the sales unit price of the minimum dosage unit and is included in data group B; Take the third row as an example: if the drug sales unit price 16 is within the unit price classification standard threshold, the data in this row is considered to be uploaded according to the minimum packaging unit and is included in data group A; Take the fourth row as an example: the drug sales unit price of 0.1 is outside the unit price classification standard threshold, and if the sales unit price * minimum package quantity is distributed outside the unit price classification standard threshold range, this part of the data is considered to be abnormal and included in data group D.

[0065] Take the drug ZA06CAX0434020103065 as an example: Take row 6 as an example: the drug sales unit price of 0.1 is outside the unit price classification standard threshold, the quantity classification standard of 100 ≠ the minimum package quantity of 1, the sales unit price * quantity classification standard is within the unit price classification standard threshold range, but the sales unit price * minimum package quantity is outside the unit price classification standard threshold range. This part of the data is considered to be uploaded as less than the minimum dosage unit and is included in data group C; Step 4: After the data is grouped, the sales unit price and sales quantity are converted to obtain the sales price and quantity under the actual minimum packaging unit, as shown in Table 5.

[0066] Group A data is considered to be data uploaded normally according to the packaging unit, and the management sales price = sales unit price, and the management sales quantity = sales quantity; Group B data is considered to be uploaded according to the minimum dosage unit, and the management sales price = sales unit price * sales quantity, and the management sales quantity = sales quantity / minimum packaging quantity; Group C data is considered to be uploaded according to smaller dosage units, and the management sales price = sales unit price * quantity classification standard, and the management sales quantity = sales quantity / quantity classification standard; Group D contains abnormal data that deviates from the normal value and no price conversion is performed.

[0067] Table 5 Sales unit price and sales quantity governance conversion results

[0068] Example 2 This embodiment provides a drug data governance system based on price conversion, including: The data docking and processing module is used to obtain detailed data on medical insurance drug costs, and after data cleaning, it is mapped with the medical insurance drug catalog to achieve data fusion and form the drug data to be analyzed; The drug price conversion module is used to formulate drug data classification standards, group the cleaned medical insurance drug cost details data, and realize drug price conversion. It cannot convert data that deviates from normal. The abnormal data processing module is used to further process data that deviates from normal data and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

[0069] Specifically, the data docking processing module 1 is used to obtain medical insurance drug cost data, map it with the medical insurance drug catalog after data cleaning, realize data fusion, and form drug data to be analyzed. This module includes a drug data collection module 101, a drug data cleaning module 102, and a drug catalog data docking module 103.

[0070] The drug data collection module 101 is used to obtain detailed data on medical insurance drug expenses and integrate multi-source heterogeneous data into data with a unified structure. The data should at least include key information such as the drug medical insurance catalog code, drug name, sales quantity, sales unit price, and total sales price.

[0071] The drug data cleaning module 102 formulates data cleaning rules to clean the drug cost detail data, cleaning out abnormal data with sales unit price less than or equal to 0, sales quantity less than or equal to 0, and missing data.

[0072] The drug catalog data docking module 103 maps the cleaned medical insurance drug expense details data with the medical insurance drug catalog, obtains the corresponding medical insurance drug catalog data, and merges the cleaned medical insurance expense details data with the medical insurance drug catalog data to form the drug data to be analyzed.

[0073] Drug Price Conversion Module 2 is used to establish drug data classification standards, group the cleaned medical insurance drug expense details data, and implement drug price conversion. Data that cannot be converted will be considered as deviated data. This module includes a drug data classification standard generation module 201, a drug data grouping module 202, a drug price conversion module 203, and a classification data generation module 204.

[0074] The drug data classification standard generation module 201 is used to generate drug data classification standards, including drug unit price classification standards, drug quantity classification standards and unit price classification standard thresholds.

[0075] The drug data grouping module 202 classifies the unit price and quantity data in the cleaned medical insurance drug expense details data according to the drug data classification standard and data classification rules, and includes the corresponding classified data into the corresponding data group.

[0076] The medicine price conversion module 203 converts the data of groups A, B and C into the minimum packaging unit price according to the data grouping situation and the data conversion rules of different groups.

[0077] The classified data generating module 204 is used to summarize and export different types of data, including detailed drug data after price conversion and abnormal data that deviates from normal values.

[0078] The abnormal data processing module 3 is used to further process the data that deviates from the normal state and identify abnormally high-price uploads and abnormal data uploads. This module includes a normality test module 301, a 3σ principle abnormality identification and processing module 302, a box plot abnormality processing module 303 and an abnormal data generation module 304.

[0079] The normality test module 301 is used to perform a normality test on the data distribution to determine whether the data obeys or approximately obeys the normal distribution.

[0080] The 3σ principle anomaly identification and processing module 302 adopts the 3σ principle outlier processing method for data that obeys or approximately obeys the normal distribution, identifies and marks data with prices greater than μ+3σ as data uploaded at abnormally high prices, and identifies and marks data with prices less than μ-3σ as data uploaded with abnormal data.

[0081] The box plot anomaly processing module 303 uses a box plot outlier processing method to identify data uploaded at abnormally high prices and data uploaded with abnormal data. Maximum and minimum estimated values ​​are calculated, and values ​​above the maximum estimated value are marked as data uploaded at abnormally high prices, while values ​​below the minimum estimated value are marked as data uploaded with abnormal data.

[0082] The abnormal data generation module 304 is used to summarize and export classified abnormal data, including data that deviates from normal data, data uploaded at abnormally high prices, and data uploaded with abnormal data.

[0083] The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment 1. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0084] The descriptions of the various embodiments in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] The proposed system can be implemented in other ways. For example, the system embodiment described above is merely illustrative. For example, the above module division is only a logical function division. In actual implementation, other division methods may be used. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not implemented.

[0086] Example 3 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the drug data governance method based on price conversion as described in the first embodiment above are implemented.

[0087] Example 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a drug data governance method based on price conversion as described in the first embodiment above are implemented.

[0088] Example 5 This embodiment provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the drug data governance method based on price conversion described in the first embodiment above.

[0089] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0090] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0093] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0094] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A drug data governance method based on price conversion, characterized in that: include: Obtain detailed data on medical insurance drug costs, clean the data, and then map it with the medical insurance drug catalog to generate drug data to be analyzed; Generate drug data classification standards based on the drug data to be analyzed; Set data grouping and classification rules according to the drug data classification standards. Classify the cleaned medical insurance drug expense details data based on the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data and include them in the corresponding data groupings. The cleaned medical insurance drug expense details are managed according to different data groups and uniformly converted to the minimum package price. Data that cannot be converted is marked as deviating from normal data. Further identify and process data that deviates from the normal state, and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

2. The drug data management method based on price conversion according to claim 1, characterized in that: The detailed data of medical insurance drug costs is obtained and mapped with the medical insurance drug catalog after data cleaning to form the drug data to be analyzed, specifically: Obtain detailed data on medical insurance drug costs, including drug medical insurance catalog code, drug name, sales quantity, and sales unit price; Perform data cleaning on the acquired medical insurance drug expense details data to obtain cleaned medical insurance drug expense details data; Based on the cleaned medical insurance drug cost details data, it is mapped with the medical insurance drug catalog to obtain the corresponding medical insurance drug catalog data; among them, the medical insurance drug catalog data includes the medical insurance catalog code, medical insurance catalog name, minimum packaging quantity, whether it is listed online, and the online price.

3. The drug data management method based on price conversion according to claim 1, characterized in that: The drug data classification standard is generated based on the drug data to be analyzed, specifically: The drug data classification standards include drug unit price classification standards, drug quantity classification standards and unit price classification standard thresholds; Calculate the drug unit price classification standard based on the sales unit price in the medical insurance drug sales expense details and the corresponding drug catalog data; Calculate the drug quantity classification standard based on the sales quantity of the medical insurance drug sales expense details and the corresponding drug catalog data; The unit price classification standard threshold is calculated based on the sales unit price and drug unit price classification standard in the medical insurance drug sales expense details.

4. The method for managing drug data based on price conversion according to claim 1, characterized in that: The data grouping and classification rules are set according to the drug data classification standard, and the cleaned medical insurance drug expense details data are classified according to the classification rules and the sales unit price and sales quantity in the cleaned medical insurance drug expense details data, specifically as follows: Set data groups, including data sets uploaded according to the minimum packaging unit as Group A, data sets uploaded according to the minimum preparation unit as Group B, data sets uploaded according to less than the minimum preparation unit as Group C, and data sets deviating from the normal range as Group D; If the sales unit price distribution is within the unit price classification standard threshold range, it will be included in data group A; If the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard = minimum package quantity, then: if the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, it will be included in data group B; if the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, it deviates from the normal range and is included in data group D; If the sales unit price distribution is outside the unit price classification standard threshold range, and the drug quantity classification standard ≠ minimum package quantity, then: If the sales unit price * minimum package quantity distribution is within the unit price classification standard threshold range, but the sales unit price * drug quantity classification standard distribution is outside the unit price classification standard threshold range, it will be included in data group B; If the sales unit price * drug quantity classification standard distribution is within the unit price classification standard threshold range, but the sales unit price * minimum package quantity distribution is outside the unit price classification standard threshold range, the data will be included in group C; If the sales unit price * quantity classification standard and the sales unit price * minimum package quantity are both distributed within the unit price classification standard threshold range, then: if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, and the sales quantity can be divided evenly by the quantity classification standard, it is included in data group C; if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, the sales quantity cannot be divided evenly by the quantity classification standard, but the sales quantity can be divided evenly by the minimum package quantity, it is included in data group B; if the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard is less than the difference between the sales unit price * minimum package quantity and the drug unit price classification standard, the sales quantity cannot be divided evenly by the quantity classification standard, and the sales quantity If the quantity cannot be divided evenly into the minimum package quantity, it shall be included in data group C; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, and the sales quantity can be divided evenly into the minimum package quantity, it shall be included in data group B; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, the sales quantity cannot be divided evenly into the minimum package quantity, but the sales quantity can be divided evenly into the quantity classification standard, it shall be included in data group C; if the difference between the sales unit price * minimum package quantity and the drug unit price classification standard is less than the difference between the sales unit price * drug quantity classification standard and the drug unit price classification standard, the sales quantity cannot be divided evenly into the minimum package quantity, and the sales quantity cannot be divided evenly into the quantity classification standard, it shall be included in data group B; If the sales unit price*quantity classification standard and the sales unit price*minimum package quantity are both distributed within and outside the unit price classification standard threshold range, they are included in data grouping group D.

5. The method for managing drug data based on price conversion according to claim 1, characterized in that: The cleaned medical insurance drug expense details data are managed according to different data groups and uniformly converted into the minimum package price. Data that cannot be converted are marked as deviating from normal data, specifically: Group A data is the cleaned medical insurance drug expense details data uploaded according to the normal packaging unit. The management sales price = sales unit price, and the management sales quantity = sales quantity. Group B data belongs to the cleaned medical insurance drug cost details data uploaded according to the minimum dosage unit. The management sales price = sales unit price * sales quantity, and the management sales quantity = sales quantity / minimum packaging quantity; Group C data belongs to the cleaned medical insurance drug cost details data uploaded based on units smaller than the minimum dosage unit. The management sales price = sales unit price * quantity classification standard, and the management sales quantity = sales quantity / quantity classification standard; The data group D belongs to the medical insurance drug cost details data after cleaning that deviates from the normal value and is marked as deviating from the normal data.

6. The method for managing drug data based on price conversion according to claim 1, characterized in that: The further identification and processing of data that deviates from the normal state, identifying data uploaded at abnormally high prices and data uploaded with abnormal data, is specifically as follows: Conduct normality tests on the sales unit prices of the same type of drugs in data that deviate from the normal distribution. For data that follow a normal distribution or approximately follow a normal distribution, use the 3σ principle to identify data uploaded with abnormally high prices and data with abnormalities. For data that deviates from normal distribution and does not follow the normal distribution, the box plot outlier processing method is used to identify data uploaded at abnormally high prices and data uploaded with abnormal data.

7. A drug data management system based on price conversion, characterized by: include: The data docking and processing module is used to obtain detailed data on medical insurance drug costs, and after data cleaning, it is mapped with the medical insurance drug catalog to achieve data fusion and form the drug data to be analyzed; The drug price conversion module is used to formulate drug data classification standards, group the cleaned medical insurance drug cost details data, and realize drug price conversion. Data that cannot be converted will deviate from normal data. The abnormal data processing module is used to further process data that deviates from normal data and identify data uploaded at abnormally high prices and data uploaded with abnormal data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the drug data governance method based on price conversion as described in any one of claims 1 to 6 are implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the steps in the drug data governance method based on price conversion as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps in the drug data governance method based on price conversion as described in any one of claims 1 to 6.

Images