CN111383732A - Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification - Google Patents
Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification Download PDFInfo
- Publication number
- CN111383732A CN111383732A CN202010207438.2A CN202010207438A CN111383732A CN 111383732 A CN111383732 A CN 111383732A CN 202010207438 A CN202010207438 A CN 202010207438A CN 111383732 A CN111383732 A CN 111383732A
- Authority
- CN
- China
- Prior art keywords
- data
- medicine
- drug
- audited
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H20/13—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered from dispensers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The invention discloses a medicine auditing method, a device, a computer system and a readable storage medium based on mutual exclusion identification, which relate to the field of medicine data analysis and comprise the following steps: collecting recording data, and preprocessing the recording data to obtain sample data; calculating the similarity of each piece of medicine data, and acquiring the medicine data with the similarity meeting a preset first condition to generate first processing data; calculating the correlation degree of each medicine data to obtain second processing data; generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data; the method comprises the steps of obtaining information of a to-be-audited drug order, auditing the information of the to-be-audited drug order based on the target data, obtaining an audit result, solving the problems that in the prior art, the audit of the mutually exclusive drugs is delayed, the omission probability is high, and the accuracy of the audit result is affected, and improving the audit accuracy.
Description
Technical Field
The invention relates to the technical field of medical data analysis, in particular to a medicine auditing method and device based on mutual exclusion identification, a computer system and a readable storage medium.
Background
Due to the existence of medical insurance fraud and unreasonable medical behaviors, medical insurance wind control is of great importance to the supervision of medical insurance funds, and with the continuous progress of science and technology, the medical insurance wind control adopts big data combined with an artificial intelligence technology to form a wind control model system for fighting against fraud and fraud.
The inventor of the invention finds in research that in a medical insurance wind control auditing process, the suitability of prescription medication needs to be audited, particularly for the identification of mutually exclusive medicines which are medicines with the same function and appear in the same prescription, the existing auditing of the mutually exclusive medicines is generally based on database comparison operation sorted by professional experience, and the database needs to be updated manually based on business knowledge, so that the delay is high, the omission probability is high, and the accuracy of an auditing result is further influenced.
Disclosure of Invention
The invention aims to provide a medicine auditing method, a medicine auditing device, a computer system and a readable storage medium based on mutual exclusion identification, which are used for solving the problems that in the prior art, the auditing of mutual exclusion medicines has delay and the omission probability is higher, so that the accuracy of an auditing result is influenced.
In order to achieve the above object, the present invention provides a method for auditing a medicine based on mutual exclusion identification, which comprises: collecting recording data, and preprocessing the recording data to obtain sample data;
wherein the sample data comprises at least one drug order information, each drug order information comprising at least one drug data;
calculating the similarity of each piece of medicine data, and acquiring the medicine data with the similarity meeting a preset first condition to generate first processing data;
calculating the correlation degree of each medicine data to obtain second processing data;
generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data;
and acquiring the information of the drug order to be audited, auditing the information of the drug order to be audited based on the target data, and acquiring an audit result.
Further, preprocessing the recorded data to obtain sample data, including the following steps:
acquiring patient information and drug order information corresponding to each patient based on the recorded data;
counting the occurrence frequency of each medicine data in each medicine order, and screening the medicine data with the occurrence frequency lower than a preset threshold value as non-analysis medicine data;
and discarding the non-analyzed drug data and synchronously adjusting corresponding drug order information to obtain sample data.
Further, calculating the similarity of each piece of the medicine data, and acquiring the medicine data with the similarity meeting a preset first condition to generate first processing data, including the following steps:
obtaining each drug data based on the sample data, and carrying out vectorization processing on each drug data to obtain a vector corresponding to each drug data;
calculating similarity values of the medicine data and other medicine data one by adopting cosine similarity;
taking a medicine data set with a similarity value larger than a preset first threshold value with any medicine data as a similar medicine data set corresponding to the medicine data;
and acquiring all the medicine data and corresponding similar medicine data sets to generate first processing data.
Further, calculating the correlation of each of the drug data, and acquiring second processing data, including the following steps:
acquiring the drug order data, and acquiring patient information and drug data based on the drug order data;
generating a state matrix for each drug used by the patient based on the patient information and the drug data;
calculating the correlation among the medicine data based on the state matrix to obtain a correlation value;
and acquiring correlation values among the medicine data to generate second processing data.
Further, acquiring information of a to-be-audited drug order, and generating a mutually exclusive drug data set corresponding to each drug data as target data based on the first processing data and the second processing data includes the following steps:
obtaining any medicine data and a corresponding similar medicine data set from the first processing data;
acquiring correlation values between the medicine data and the similar medicine data in the similar medicine data set based on the second processing data;
acquiring similar medicine data with a correlation value meeting a preset second condition with the medicine data to generate a mutually exclusive medicine data set corresponding to the medicine data;
and acquiring all the medicine data and corresponding mutually exclusive medicine data sets as target data.
Further, auditing the to-be-audited drug order information based on the target data, and obtaining an auditing result, including the following steps:
acquiring data of the drug to be checked based on the information of the drug list to be checked;
retrieving whether mutually exclusive medicine data corresponding to any medicine data to be audited exists in the information of the medicine list to be audited based on the target data;
if yes, the checking result is not passed;
if not, the result of the audit is passed.
Further, retrieving whether mutually exclusive drug data corresponding to a certain drug data to be audited exists in the drug order information to be audited based on the target data includes the following steps:
acquiring any one piece of data of the drug to be checked based on the information of the drug list to be checked;
searching a mutually exclusive medicine data set matched with the medicine data to be audited in the target data;
retrieving the residual to-be-audited medicine data in the to-be-audited medicine bill information based on the mutually exclusive medicine data set;
if the drug data consistent with the similar drug data set is retrieved, mutually exclusive drug data corresponding to the drug data to be audited exists in the drug list information to be audited;
and if the medicine data consistent with the similar medicine data set is not retrieved, the mutually exclusive medicine data corresponding to the medicine data to be audited does not exist in the information of the medicine list to be audited.
In order to achieve the above object, the present invention further provides a medicine auditing apparatus based on mutual exclusion identification, including:
the system comprises a preprocessing module, a storage module and a display module, wherein the preprocessing module is used for acquiring recorded data and preprocessing the recorded data to obtain sample data, the sample data comprises at least one piece of drug order information, and each piece of drug order information comprises at least one piece of drug data;
the first processing module is used for calculating the similarity of the medicine data, acquiring the medicine data with the similarity meeting a preset first condition and generating first processing data;
the second processing module is used for calculating the correlation degree of each piece of medicine data and acquiring second processing data;
the comprehensive module is used for generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data;
and the auditing module is used for acquiring the information of the drug order to be audited, auditing the information of the drug order to be audited based on the target data and acquiring an auditing result.
To achieve the above object, the present invention also provides a computer system comprising at least one computer device, each computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor of the at least one computer device jointly implementing the steps of the above method when executing the computer program.
To achieve the above object, the present invention further provides a computer-readable storage medium comprising a plurality of storage media, each storage medium having stored thereon a computer program, the computer programs stored in the storage media, when executed by a processor, collectively implementing the steps of the above method.
According to the medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification, the recorded data are automatically collected and analyzed to obtain the mutual exclusion medicine set as the target data, and then the auditing module is adopted to automatically audit the information of the medicine list to be audited, so that the auditing process of the information of the medicine list is completed, manual operation is reduced, and the problems that the auditing of the mutual exclusion medicine in the prior art is delayed, the omission probability is high and the accuracy of the auditing result is influenced are solved.
Drawings
FIG. 1 is a flowchart illustrating a first embodiment of a method for auditing a medicine based on mutual exclusion identification according to the present invention;
FIG. 2 is a flowchart illustrating a method for auditing a medicine based on mutual exclusion identification according to a first embodiment of the present invention, in which the recorded data is preprocessed to obtain sample data;
fig. 3 is a flowchart illustrating a first process of generating first process data by calculating similarity of each piece of drug data and acquiring drug data with the similarity satisfying a preset first condition according to a first embodiment of a mutual exclusion identification-based drug auditing method according to the present invention;
FIG. 4 is a flowchart illustrating a first embodiment of a method for auditing medicines based on mutual exclusion identification according to the present invention, wherein a correlation degree of each medicine data is calculated to obtain second processing data;
fig. 5 is a flowchart illustrating a first embodiment of a method for auditing a medicine based on mutual exclusion identification according to the present invention, where a mutually exclusive medicine data set corresponding to each medicine data is generated as target data based on the first processed data and the second processed data;
fig. 6 is a flowchart illustrating a process of acquiring information of a to-be-audited drug order, auditing the information of the to-be-audited drug order based on the target data, and acquiring an audit result in the first embodiment of the mutually exclusive identification-based drug audit method according to the present invention;
fig. 7 is a flowchart illustrating that, in a first embodiment of the mutually exclusive identification-based drug audit method according to the present invention, for example, any one piece of drug data to be audited is processed, and whether mutually exclusive drug data corresponding to the drug data to be audited exists in the drug order information to be audited is retrieved based on the target data;
FIG. 8 is a block diagram illustrating a second embodiment of a mutual exclusion identification based drug audit device according to the present invention;
FIG. 9 is a block diagram illustrating an audit module of a second embodiment of a mutually exclusive identity-based drug audit device according to the present invention;
fig. 10 is a schematic diagram of a hardware structure of a computer device in the third embodiment of the computer system according to the present invention.
Reference numerals:
71. preprocessing module 72, first processing module 73, second processing module
74. Integration module 75, audit module 741, first acquisition unit
742. Matching unit 743, screening unit 744, second acquisition unit
81. Memory 82 and processor
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a medicine auditing method, a device, a computer system and a readable storage medium method based on mutual exclusion identification, which are applicable to the technical field of computers and are based on a preprocessing module, a first processing module, a second processing module, a comprehensive module and an auditing module. The invention acquires the recorded data through the preprocessing module, records the data as the record of the drug order issued by the professional based on the specific disease, preprocesses the recorded data to obtain the sample data, the sample data is the primarily processed drug order information, processes the sample data by adopting the first processing module and the second processing module, calculates the similarity and the correlation of each drug data on the drug order information, processes the result processed by the first processing module and the second processing module again by adopting the comprehensive module, obtains the mutually exclusive drug data corresponding to each drug data as the target data based on the correlation between each drug data and the similar drug, compares the drug data on the drug order to be audited with the target data by adopting the comprehensive module, judges whether two or more than two mutually exclusive drug data exist on the drug order to be audited, if the check result exists, the check is not passed, the existing recorded data is collected through the mode, then the medicine data with mutual exclusivity is obtained based on the similarity and the correlation, and the check mode is carried out by taking the data as a standard, so that the problems that the check of the mutual exclusivity medicine in the prior art has delay, the omission probability is high, and the accuracy of the check result is influenced are solved.
Example one
Referring to fig. 1, the present embodiment provides a method for auditing a medicine based on mutual exclusion identification, as shown in fig. 1, including the following steps:
s1: collecting recording data, and preprocessing the recording data to obtain sample data;
in the above embodiment, the collected record data is a prescription record of each patient in a specific disease (such as diabetes) acquired through a platform, each record data includes patient information, drug order information corresponding to the patient information, and drug data in each drug order, and it should be noted that, in this embodiment, the drug orders are drug data sets prescribed by professionals for different patients, the drug data is a drug name, and the drug name is a professional name and can be directly acquired from the platform, for example: dexamethasone, rosiglitazone and the like, wherein each medicine data corresponds to a medicine, and the follow-up medicines are consistent with the medicine data.
Specifically, the preprocessing is performed on the recorded data to obtain sample data, referring to fig. 2, which includes the following steps:
s11: acquiring patient information and drug order information corresponding to each patient based on the recorded data;
each patient corresponds to at least one piece of drug order information, and some patients can correspond to a plurality of pieces of drug order information; each drug order message contains at least one drug data, such as: patient a- { glipizide, repaglinide, metformin hydrochloride }; patient B- { glipizide, repaglinide, miglitol }
S12: counting the occurrence frequency of each medicine data in each medicine order, and screening the medicine data with the occurrence frequency lower than a preset threshold value as non-analysis medicine data;
s13: and discarding the non-analyzed drug data and synchronously adjusting corresponding drug order information to obtain sample data.
Wherein the sample data also comprises at least one drug order information, each drug order information comprising at least one drug data.
In the above embodiment, the drug data with a frequency lower than the threshold occurs, and such drug data may be drug data used based on patient personalization or special condition consideration, which affects the accuracy of the analysis result of subsequent sample data, and causes an error to the analysis result of the specific disease in the embodiment, and such drug data is discarded, and such drug data is not analyzed, so that the quality of the sample data can be improved, and the accuracy of the target data finally obtained based on the sample data in the subsequent S2, S3, and S4 is further improved.
It should be noted that when the non-analyzed drug data appears in the to-be-checked drug information sheet in the subsequent S5, the similarity and the correlation determination process of the non-analyzed drug data are consistent, and a drug determined as a low frequency of occurrence may be found, where the similarity between the non-analyzed drug data and the analyzed drug data is 0 or not, and the drug with the low frequency of occurrence only represents an uncommon use and does not represent a similarity or correlation with other drugs.
S2: calculating the similarity of each piece of medicine data, and acquiring the medicine data with the similarity meeting a preset first condition to generate first processing data;
specifically, S2 includes the following steps, see fig. 3:
s21: obtaining each drug data based on the sample data, and carrying out vectorization processing on each drug data to obtain a vector corresponding to each drug data;
in this embodiment, vectorization processing is implemented by using a word2vec model, obtaining a vector corresponding to each piece of medicine data, obtaining a word vector by using the word2vec model is a common means in the prior art, obtaining a word vector corresponding to each piece of medicine data by using other models in the prior art can also be used for this purpose, the word2vec model is a word vector space submerged model in natural language processing, the model is a shallow and double-layer neural network, and after training is completed, the word2vec model can be used for mapping each word to a vector and can be used for representing a word-to-word relationship.
The word2vec model training process comprises the following steps: firstly establishing an initial word2vec model and obtaining a training sample, counting the occurrence frequency of each word in the training sample, storing the number in a hash table, establishing a Huffman tree according to the word frequency of each word, initializing a word vector and a vector of a non-leaf node of the Huffman tree, calculating a gradient by using gradient descent, updating the value of the word vector and the word of the vector at the non-leaf node, executing training, adjusting the initial word2vec model to enable the output result to be consistent with that in the training sample until the training process is completed, and obtaining a trained target model. And subsequently, inputting the medicine data into the target model to obtain the word vector corresponding to each medicine data.
S22: calculating similarity values of the medicine data and other medicine data one by adopting cosine similarity;
word vector α (x) corresponding to drug data A1，x2，…，xi，…xn) Word vector β (y) corresponding to drug data B1，y2，…，yi，…yn) For example, the cosine similarity between vector α and vector β is calculated as follows:
wherein Cos (theta) is a cosine value of an included angle theta between the two vectors.
Cosine similarity measures the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space. The cosine value is closer to 1, which indicates that the included angle is closer to 0 degree, namely the two vectors are more similar, which is called cosine similarity.
S23: taking a medicine data set with a similarity value larger than a preset first threshold value with any medicine data as a similar medicine data set corresponding to the medicine data; first processing data is generated based on all the drug data and the corresponding similar drug data sets.
Specifically, in S2, the first preset condition is greater than a preset first threshold.
Based on the above cosine similarity calculation formula, obtaining a cosine similarity value between any two pieces of medicine data, judging whether the two pieces of medicine data are similar based on the cosine similarity value, judging whether the two pieces of medicine data are similar based on a preset first threshold value, judging whether the two pieces of medicine data are similar based on the cosine similarity value, judging whether the two pieces of medicine data are similar based on the preset first threshold value, judging whether the two pieces of medicine data are not similar based on the preset first threshold value, and calculating the similarity of each piece of medicine data with other pieces of medicine data one by one, so as to obtain a similar medicine data set corresponding to each piece of medicine data, namely a: { drug j, drug k, drug 1 … … drug n }, all drug data and their corresponding similar drug sets are the first processing data.
S3: calculating the correlation degree of each medicine data to obtain second processing data;
specifically, referring to fig. 4, S3 includes the following steps:
s31: acquiring the drug order data, and acquiring patient information and drug data based on the drug order data;
s32: generating a state matrix for each drug used by the patient based on the patient information and the drug data;
in this embodiment, the state matrix represents one patient in one row and one drug in one column, and correlation values between two adjacent columns are calculated.
Specifically, the correlation calculation formula is:
x and Y are respectively two adjacent columns of data in the matrix, r (X and Y) is a correlation value of the two adjacent columns, and Cov () is used for calculating the covariance of the two columns of data and measuring the total error of two variables; var () is a variance that is used to measure the degree of deviation between a random variable and its mathematical expectation (i.e., mean).
S33: calculating the correlation among the medicine data based on the state matrix to obtain a correlation value;
the value of r (X, Y) in the above similarity calculation formula is between-1 and 1. When r is positive, it is positively correlated, reflecting that when x increases (decreases), y increases (decreases) accordingly; when r is negative, it is a negative correlation, reflecting that as x increases (decreases), y decreases (increases) accordingly; the larger the absolute value of r, the higher the degree of correlation between variables.
S34: and acquiring correlation values among the various drug data to generate second processing data.
By way of example and not limitation, the second processing data may be that the drug data a and the drug data b have a correlation value of 0.34, the drug data a and the drug data c have a correlation value of-0.78, and so on.
S4: generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data;
specifically, referring to fig. 5, the S4 includes the following steps:
s41: obtaining any medicine data and a corresponding similar medicine data set from the first processing data;
s42: acquiring correlation values between the medicine data and the similar medicine data in the similar medicine data set based on the second processing data;
it should be noted that, similar drug data sets corresponding to drug data are obtained through the first processing data, correlations between the drug data and each similar drug are obtained through the second processing data, and non-related drug data in similar drug data corresponding to a certain drug data is a mutually exclusive drug data set corresponding to the drug data.
S43: acquiring similar medicine data with a correlation value meeting a preset second condition with the medicine data to generate a mutually exclusive medicine data set corresponding to the medicine data;
in this embodiment, it is noted that, in the embodiment, since the purpose of the audit is to prevent the occurrence of the mutually exclusive drug data in the drug order information, that is, the mutually exclusive drug needs to be screened out as the comparison data for comparison in the subsequent S5, the absolute value of the correlation is smaller than the preset second threshold, and it can be said that the correlation between two similar drug data is not large when the preset second condition is satisfied, that is, the correlation between any two similar drug data can be obtained based on the similarity result, and the correlation between two similar drug data is defined as being correlated or not correlated by the preset second condition, when the correlation between the similar drugs corresponding to a certain drug data is smaller than the preset second threshold, the similar drug is the mutually exclusive drug corresponding to the drug data.
S44: and acquiring all the medicine data and corresponding mutually exclusive medicine data sets as target data.
In the above embodiment, taking the drug data m as an example, the first process obtains a set of similar drugs corresponding to each drug, for example: drug m similar drug data set P: { drug j, drug k, drug 1, drug n }, the second process obtains correlation values between the individual drugs, such as: the correlation between the medicine m and the medicine j, and the medicine j exceeds a preset second threshold, that is, the preset second condition is not met, the correlation value between the medicine m and the medicine 1, and the medicine n is lower than the preset second threshold, and the preset second condition is met, that is, the medicine m and the medicine 1, and the medicine n are not correlated, then the first processing data and the second processing data can obtain the mutually exclusive data set Q { medicine 1, medicine n } correlated with the medicine data m, and all the medicine data in the sample data and the respectively correlated mutually exclusive data set are the target data.
The method and the device can acquire the similar medicine data set of each medicine data in the current record through the similarity, judge whether the two medicines are mutually exclusive medicines or not by calculating the correlation between the two similar medicine data, ensure the judgment accuracy, and have the advantages of simple and convenient operation and higher working efficiency.
S5: and acquiring the information of the drug order to be audited, auditing the information of the drug order to be audited based on the target data, and acquiring an audit result.
Specifically, the step S5 includes the following steps, see, 6:
s51: acquiring data of the drug to be checked based on the information of the drug list to be checked;
based on the recorded data in S1, the to-be-audited drug order and the drug order information in the recorded data are of the same type, and are all drug data sets prescribed by the professional for the patient, and the to-be-audited drug order information includes a plurality of to-be-audited drug data.
S52: retrieving whether mutually exclusive drug data corresponding to the drug data to be audited exist in the drug list information to be audited based on the target data;
more specifically, taking processing any one piece of data of the drug to be checked as an example, retrieving, based on the target data, whether mutually exclusive drug data corresponding to the data of the drug to be checked exists in the information of the drug order to be checked, referring to fig. 7, the following steps are included:
s521: acquiring any one piece of data of the drug to be checked based on the information of the drug list to be checked;
s522: searching a mutually exclusive medicine data set matched with the medicine data to be audited in the target data;
in the above embodiment, whether the drug data consistent with the drug data to be audited exists or not is searched in the first processing data based on the drug data to be audited, if so, a related similar drug data set is obtained, that is, a mutually exclusive drug data set matched with the drug data to be audited is obtained, and if not, the audit result is passed.
S523: retrieving the residual to-be-audited medicine data in the to-be-audited medicine bill information based on the mutually exclusive medicine data set;
in this step, the purpose of searching the remaining to-be-checked drug data in the to-be-checked drug order information is to find whether there is drug data similar to the to-be-checked drug data, taking the drug data m as an example, the corresponding mutually exclusive drug set Q { drug 1, drug n }, and the to-be-checked drug order information is a { drug m, drug o, drug c, drug h, drug l }, it can be found that there is drug data mutually exclusive with the drug data m in the to-be-checked drug order that there is drug 1 through searching.
S524: if the drug data consistent with the similar drug data set is retrieved, mutually exclusive drug data corresponding to the drug data to be audited exists in the drug list information to be audited;
based on the example in S523 above, at this time, the drug data m and the drug data 1 are mutually exclusive, and then the search process of the next drug data, such as the drug o, is performed until the search of the similar drug data corresponding to all the drug data is completed.
And when all the data of the medicines to be audited on the medicine list to be audited are searched, and the information of the medicine data m of the medicine list to be audited and the medicine data 1 are mutually exclusive, the situation that mutually exclusive medicines exist on the medicine list to be audited is indicated, and the audit result is that the medicines do not pass.
S525: and if the medicine data consistent with the similar medicine data set is not retrieved, the mutually exclusive medicine data corresponding to the medicine data to be audited does not exist in the information of the medicine list to be audited.
Specifically, when all the data of the drug to be audited on the drug list to be audited are retrieved and the information of the drug list to be audited does not have the mutually exclusive drug data of any one data of the drug to be audited, it indicates that the mutually exclusive drug does not exist on the drug list to be audited, and the audit result is passed.
After one piece of data of the drug to be checked is completed through S521-S525, another piece of data of the drug to be checked is obtained again to be processed until all pieces of data of the drug to be checked are processed.
S53: if yes, the checking result is not passed;
s54: if not, the auditing result is passed;
according to the method and the device, all the record data corresponding to the specific diseases can be acquired, then the similarity and correlation identification are carried out on the medicine data in the record data, the medicine data possibly having the mutual exclusion relationship, namely the target data, is obtained and compared with the medicine data in the medicine list to be audited, the identification of the mutual exclusion medicines in the medicine list is realized, the problem of hysteresis caused by the fact that the mutual exclusion medicines are identified by relying on manual experience in the prior art to establish data is solved, the accuracy and the instantaneity of the target comparison data are improved, and further the accuracy of the follow-up audit result is improved.
Example two
Referring to fig. 8, a medicine auditing device 7 based on mutual exclusion identification of the embodiment includes
The preprocessing module 71 is configured to collect recording data, preprocess the recording data to obtain sample data, where the sample data includes at least one piece of drug order information, and each piece of drug order information includes at least one piece of drug data;
the first processing module 72 is configured to calculate similarity of each piece of the drug data, and acquire drug data with the similarity meeting a preset first condition to generate first processing data;
the second processing module 73 is configured to calculate a correlation degree of each piece of medicine data, and obtain second processing data;
a synthesis module 74, configured to generate, based on the first processing data and the second processing data, a mutually exclusive drug data set corresponding to each drug data as target data;
in the above embodiment, each piece of drug data and its corresponding similar drug data set are obtained by the first processing module; the correlation degree between the medicine data can be obtained through the second processing module; and acquiring the correlation degree between each medicine data and each form medicine by adopting the comprehensive module based on the correlation degree between each medicine data, and acquiring a similar and non-correlated medicine corresponding to a certain medicine as a mutually exclusive medicine of the medicine, namely the medicine and the mutually exclusive medicine are not simultaneously appeared on the same audit medicine list.
The auditing module 75 is configured to acquire the information of the drug order to be audited, audit the information of the drug order to be audited based on the target data, and acquire an auditing result;
with reference to fig. 9, the synthesis module 74 further includes the following:
a first obtaining unit 741, configured to obtain any one of the drug data and a corresponding similar drug data set from the first processing data;
a matching unit 742, configured to obtain, based on the second processing data, a correlation value between the drug data and each similar drug data in a similar drug data set;
a screening unit 743, configured to obtain similar drug data with a correlation value lower than a preset second condition with the drug data, and generate a mutually exclusive drug data set corresponding to the drug data;
a second obtaining unit 744, configured to obtain all the medicine data and the corresponding mutually exclusive medicine data set as target data.
The technical scheme is based on a big data engine in data analysis, utilizes a preprocessing module to collect record data corresponding to a certain specific disease from a platform, preprocesses the record data, namely eliminates the medicine data which are not commonly used, so as to reduce the influence on subsequent target data, obtains sample data, performs similarity analysis on the sample data by a first processing module to obtain a similar medicine data set corresponding to each medicine data, adopts a second processing module to perform correlation calculation on each medicine data, adopts a comprehensive module to filter each medicine and similar medicines thereof based on the correlation among each medicine data, can obtain a medicine data set with lower applicability corresponding to each medicine data, namely a mutually exclusive medicine data set corresponding to each medicine data, namely the target data, completes the inspection of the information of a medicine to be inspected by an inspection module based on the target data in the inspection process, and the audit result is obtained, the automation of drug audit is completed, and the problems that the audit of the mutual exclusion drug in the prior art has delay and high omission probability, and further the accuracy of the audit result is influenced are solved.
According to the technical scheme, the audit is performed after the data are automatically acquired and the comparison data are automatically identified, the audit process of the drug order is completed, manual operation is reduced, risks caused by wrong judgment and missed judgment in the audit process are reduced, and meanwhile, more abnormal data of the drug order in the medical insurance wind control process can be mined out based on the acquired all recorded data.
Example three:
in order to achieve the above object, the present invention further provides a computer system, as shown in fig. 10, the computer system includes at least one computer device 8, and the components of the second embodiment of the drug audit device 7 based on mutual exclusion identification may be distributed in different computer devices, where the computer devices may be smartphones, tablet computers, notebook computers, desktop computers, rack servers, blade servers, tower servers, or cabinet servers (including independent servers, or a server cluster formed by multiple servers) that execute programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory 81, a processor 82, which may be communicatively coupled to each other via a system bus, as shown in FIG. 10. It should be noted that fig. 10 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.
In this embodiment, the memory 81 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 81 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 81 may be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 81 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 81 is generally used for storing an operating system and various application software installed on the computer device, such as the program code of the drug auditing method based on mutual exclusion identification in the first embodiment. Further, the memory 81 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 82 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 82 is typically used to control the overall operation of the computer device. In this embodiment, the processor 82 is configured to operate the program codes stored in the memory 81 or process data, for example, operate a data saving and querying device, so as to implement the method for checking and verifying a drug based on mutual exclusion identification according to the first embodiment.
Example four:
to achieve the above objects, the present invention also provides a computer-readable storage system including a plurality of storage media, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 82, implements corresponding functions. The computer-readable storage medium of this embodiment is used for storing a data saving and querying device, and when executed by the processor 82, the method for auditing a medicine based on mutual exclusion identification of the first embodiment is implemented.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A drug auditing method based on mutual exclusion identification is characterized by comprising the following steps:
collecting recording data, and preprocessing the recording data to obtain sample data; wherein the sample data comprises at least one drug order information, each drug order information comprising at least one drug data;
calculating the similarity of each piece of medicine data, and acquiring the medicine data with the similarity meeting a preset first condition to generate first processing data;
calculating the correlation degree of each medicine data to obtain second processing data;
generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data;
and acquiring the information of the drug order to be audited, auditing the information of the drug order to be audited based on the target data, and acquiring an audit result.
2. The method for auditing the medicines based on mutual exclusion identification according to claim 1, wherein preprocessing the recorded data to obtain sample data comprises the following steps:
acquiring patient information and drug order information corresponding to each patient based on the recorded data;
counting the occurrence frequency of each medicine data in each medicine order, and screening the medicine data with the occurrence frequency lower than a preset threshold value as non-analysis medicine data;
and discarding the non-analyzed drug data and synchronously adjusting corresponding drug order information to obtain sample data.
3. The method for auditing medicines based on mutual exclusion identification according to claim 1, wherein calculating the similarity of each of the medicine data, obtaining the medicine data whose similarity satisfies a preset first condition and generating first processing data comprises the following steps:
obtaining each drug data based on the sample data, and carrying out vectorization processing on each drug data to obtain a vector corresponding to each drug data;
calculating similarity values of the medicine data and other medicine data one by adopting cosine similarity;
taking a medicine data set with a similarity value larger than a preset first threshold value with any medicine data as a similar medicine data set corresponding to the medicine data;
and acquiring all the medicine data and corresponding similar medicine data sets to generate first processing data.
4. The method for auditing medicines based on mutual exclusion identification according to claim 1, characterized by calculating the degree of correlation of each of said medicine data to obtain second processed data; comprises the following steps:
acquiring the drug order data, and acquiring patient information and drug data based on the drug order data;
generating a state matrix for each drug used by the patient based on the patient information and the drug data;
calculating the correlation among the medicine data based on the state matrix to obtain a correlation value;
and acquiring correlation values among the medicine data to generate second processing data.
5. The method for auditing medicines based on mutual exclusion identification according to claim 1, wherein the generating a mutually exclusive medicine data set corresponding to each of the medicine data as target data based on the first processing data and the second processing data comprises the following steps:
obtaining any medicine data and a corresponding similar medicine data set from the first processing data;
acquiring correlation values between the medicine data and the similar medicine data in the similar medicine data set based on the second processing data;
acquiring similar medicine data with a correlation value meeting a preset second condition with the medicine data to generate a mutually exclusive medicine data set corresponding to the medicine data;
and acquiring all the medicine data and corresponding mutually exclusive medicine data sets as target data.
6. The method for auditing medicines based on mutual exclusion identification according to claim 1, wherein auditing the information of the medicine order to be audited based on the target data and obtaining an audit result comprises the following steps:
acquiring data of each drug to be checked based on the information of the drug list to be checked;
retrieving whether mutually exclusive medicine data corresponding to any medicine data to be audited exists in the information of the medicine list to be audited based on the target data;
if yes, the checking result is not passed;
if not, the result of the audit is passed.
7. The method for drug audit based on mutual exclusion identification as claimed in claim 6, wherein retrieving whether there is mutual exclusion drug data corresponding to a certain drug data to be audited in the drug list information to be audited based on the target data comprises the following steps:
acquiring any one piece of data of the drug to be checked based on the information of the drug list to be checked;
searching a mutually exclusive medicine data set matched with the medicine data to be audited in the target data;
retrieving the residual to-be-audited medicine data in the to-be-audited medicine bill information based on the mutually exclusive medicine data set;
if the drug data consistent with the similar drug data set is retrieved, mutually exclusive drug data corresponding to the drug data to be audited exists in the drug list information to be audited;
and if the medicine data consistent with the similar medicine data set is not retrieved, the mutually exclusive medicine data corresponding to the medicine data to be audited does not exist in the information of the medicine list to be audited.
8. A medicine auditing device based on mutual exclusion identification is characterized by comprising:
the system comprises a preprocessing module, a storage module and a display module, wherein the preprocessing module is used for acquiring recorded data and preprocessing the recorded data to obtain sample data, the sample data comprises at least one piece of drug order information, and each piece of drug order information comprises at least one piece of drug data;
the first processing module is used for calculating the similarity of the medicine data, acquiring the medicine data with the similarity meeting a preset first condition and generating first processing data;
the second processing module is used for calculating the correlation degree of each piece of medicine data and acquiring second processing data;
the comprehensive module is used for generating a mutually exclusive medicine data set corresponding to each medicine data as target data based on the first processing data and the second processing data;
and the auditing module is used for acquiring the information of the drug order to be audited, auditing the information of the drug order to be audited based on the target data and acquiring an auditing result.
9. A computer system comprising at least one computer device, each computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 1 to 7 are collectively implemented by the processor of the at least one computer device when the computer program is executed.
10. A computer-readable storage medium comprising a plurality of storage media, each storage medium having a computer program stored thereon, wherein the computer programs stored by the plurality of storage media, when executed by a processor, collectively implement the steps of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207438.2A CN111383732B (en) | 2020-03-23 | 2020-03-23 | Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207438.2A CN111383732B (en) | 2020-03-23 | 2020-03-23 | Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111383732A true CN111383732A (en) | 2020-07-07 |
| CN111383732B CN111383732B (en) | 2023-04-18 |
Family
ID=71218848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010207438.2A Active CN111383732B (en) | 2020-03-23 | 2020-03-23 | Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111383732B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113223659A (en) * | 2021-05-14 | 2021-08-06 | 北京百瑞弘霖有害生物防治科技有限责任公司 | Prescription management method and device |
| CN113223660A (en) * | 2021-05-14 | 2021-08-06 | 北京百瑞弘霖有害生物防治科技有限责任公司 | Method and device for acquiring prescription |
| WO2023175413A1 (en) * | 2022-03-15 | 2023-09-21 | International Business Machines Corporation | Mutual exclusion data class analysis in data governance |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120233188A1 (en) * | 2011-03-11 | 2012-09-13 | Arun Majumdar | Relativistic concept measuring system for data clustering |
| US9443015B1 (en) * | 2013-10-31 | 2016-09-13 | Allscripts Software, Llc | Automatic disambiguation assistance for similar items in a set |
| CN108717862A (en) * | 2018-04-10 | 2018-10-30 | 四川骏逸富顿科技有限公司 | A kind of careful square evolution model of the intelligence based on machine learning |
| CN109064294A (en) * | 2018-08-21 | 2018-12-21 | 重庆大学 | A kind of time of fusion factor, the drug recommended method of text feature and correlation |
| CN109243617A (en) * | 2018-08-17 | 2019-01-18 | 东软集团股份有限公司 | Checking method, device, storage medium and the electronic equipment of antibacterial effective prescription |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN109545319A (en) * | 2018-10-16 | 2019-03-29 | 平安科技（深圳）有限公司 | The prescription alarm method and terminal device of knowledge based relationship analysis |
| CN110210222A (en) * | 2018-10-24 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN110390021A (en) * | 2019-06-13 | 2019-10-29 | 平安科技（深圳）有限公司 | Drug knowledge mapping construction method, device, computer equipment and storage medium |
| CN110738216A (en) * | 2019-09-04 | 2020-01-31 | 南京理工大学 | Medicine identification method based on improved SURF algorithm |
-
2020
- 2020-03-23 CN CN202010207438.2A patent/CN111383732B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120233188A1 (en) * | 2011-03-11 | 2012-09-13 | Arun Majumdar | Relativistic concept measuring system for data clustering |
| US9443015B1 (en) * | 2013-10-31 | 2016-09-13 | Allscripts Software, Llc | Automatic disambiguation assistance for similar items in a set |
| CN108717862A (en) * | 2018-04-10 | 2018-10-30 | 四川骏逸富顿科技有限公司 | A kind of careful square evolution model of the intelligence based on machine learning |
| CN109243617A (en) * | 2018-08-17 | 2019-01-18 | 东软集团股份有限公司 | Checking method, device, storage medium and the electronic equipment of antibacterial effective prescription |
| CN109064294A (en) * | 2018-08-21 | 2018-12-21 | 重庆大学 | A kind of time of fusion factor, the drug recommended method of text feature and correlation |
| CN109545319A (en) * | 2018-10-16 | 2019-03-29 | 平安科技（深圳）有限公司 | The prescription alarm method and terminal device of knowledge based relationship analysis |
| CN110210222A (en) * | 2018-10-24 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN110390021A (en) * | 2019-06-13 | 2019-10-29 | 平安科技（深圳）有限公司 | Drug knowledge mapping construction method, device, computer equipment and storage medium |
| CN110738216A (en) * | 2019-09-04 | 2020-01-31 | 南京理工大学 | Medicine identification method based on improved SURF algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113223659A (en) * | 2021-05-14 | 2021-08-06 | 北京百瑞弘霖有害生物防治科技有限责任公司 | Prescription management method and device |
| CN113223660A (en) * | 2021-05-14 | 2021-08-06 | 北京百瑞弘霖有害生物防治科技有限责任公司 | Method and device for acquiring prescription |
| WO2023175413A1 (en) * | 2022-03-15 | 2023-09-21 | International Business Machines Corporation | Mutual exclusion data class analysis in data governance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111383732B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111383732B (en) | Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification | |
| US20200081899A1 (en) | Automated database schema matching | |
| CN111639535A (en) | Face recognition method and device based on deep learning | |
| CN111612041A (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| US20210326995A1 (en) | Claim settlement anti-fraud method, apparatus, device, and storage medium based on graph computation technology | |
| CN110991170A (en) | Chinese disease name intelligent standardization method and system based on electronic medical record information | |
| US20230004979A1 (en) | Abnormal behavior detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN114186760A (en) | Analysis method and system for stable operation of enterprise and readable storage medium | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN110929525B (en) | Network loan risk behavior analysis and detection method, device, equipment and storage medium | |
| CN111489105A (en) | Enterprise risk identification method, device and equipment | |
| CN111429289B (en) | Single disease identification method and device, computer equipment and storage medium | |
| CN103336800A (en) | Fingerprint storage and comparison method based on behavior analysis | |
| CN109144999B (en) | Data positioning method, device, storage medium and program product | |
| CN114495137B (en) | Bill abnormity detection model generation method and bill abnormity detection method | |
| CN115661472A (en) | Image duplicate checking method and device, computer equipment and storage medium | |
| CN115880702A (en) | Data processing method, device, equipment, program product and storage medium | |
| CN114743209A (en) | Prescription identification and verification method, system, electronic equipment and storage medium | |
| US20210342640A1 (en) | Automated machine-learning dataset preparation | |
| CN110689441B (en) | Case auditing method, device, equipment and storage medium based on commonality extraction | |
| CN111414699A (en) | Information analysis and prediction method, device, computer system and readable storage medium | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium | |
| CN112149566A (en) | Image processing method and device, electronic equipment and storage medium | |
| Ma | Clustering of Time Series Data: Measures, Methods, and Applications | |
| CN114066618A (en) | Object attribute information processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |