Hospital pharmacy prescription information intelligent management method

Abstract

The invention relates to the technical field of medical information processing, in particular to a hospital pharmacy prescription information intelligent management method. Obtaining a medication frequency characteristic value and a medication characteristic characterization value of the patient according to the doctor-seeing prescription information of the patient, and obtaining prescription characteristic points of the patient; obtaining an average difference distance according to the distance characteristics of the prescription characteristic points, and obtaining an adjustment coefficient according to the related characteristics of the medication characteristic characterization value; obtaining a basic neighborhood radius according to the average difference distance and the adjustment coefficient, and performing clustering; obtaining a heterogeneity degree and an optimization cluster according to the drug use characteristic representation value of the clustering cluster and the distance characteristic of the clustering cluster; and obtaining a compression level according to the quantity features of the prescription feature points in the optimization cluster, and compressing the prescription information. Clustering is carried out according to the characteristics of the prescription information, the clustering result is optimized, compression of different degrees is carried out according to the clustering result, and the accuracy of the compression degree of the prescription information is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to an intelligent management method for prescription information of a hospital pharmacy. Background Art

[0002] With the development of medical digitization, the hospital's information system is constantly improving. In order to facilitate doctors' diagnosis and treatment, the patient's prescription information and other information are stored in the hospital's database. Since the patient's prescription information data is too much, in order to facilitate the efficient storage and management of prescription information, it is necessary to compress and store the prescription information.

[0003] When compressing prescription information using the same compression level, the differences in size and content of prescription information for different patients are not taken into account, resulting in poor results in compressed data management; therefore, different prescription information needs to be distinguished; clustering algorithms are usually used to distinguish different types of prescription information to obtain different clustering clusters, but different settings of clustering parameters during the clustering process can easily lead to errors in the clustering results of prescription information, which in turn leads to errors in the compression level of different prescription information by the compression algorithm, affecting the accuracy of the compression level. Summary of the invention

[0004] In order to solve the technical problem that the above clustering algorithm does not accurately cluster prescription information and affects the accuracy of compression, the purpose of the present invention is to provide a method for intelligent management of hospital pharmacy prescription information. The technical solution adopted is as follows: Obtain the patient's prescription information, and obtain the patient's medication frequency characteristic value and medication characteristic representation value based on the medication type, medication frequency, medication dosage, and number of follow-up visits in the prescription information; Constructing a three-dimensional space according to the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value to obtain the prescription characteristic points of different patients, obtaining the average difference distance according to the distance characteristics between the prescription characteristic points; obtaining the adjustment coefficient according to the correlation characteristics between the medication characteristic representation values; obtaining the basic neighborhood radius of clustering according to the average difference distance and the adjustment coefficient; Clustering the prescription feature points according to the basic neighborhood radius to obtain clusters; obtaining inter-cluster difference values ​​according to the difference characteristics of the medication feature representation values ​​between clusters; obtaining the heterogeneity between clusters according to the distance characteristics between clusters and the inter-cluster difference values; The clusters are merged according to the heterogeneity to obtain an optimized cluster; a compression level is obtained according to the quantity characteristics of the prescription feature points in the optimized cluster, and the prescription information is compressed.

[0005] Furthermore, the step of obtaining the patient's medication frequency characteristic value and medication characteristic representation value according to the medication type, medication frequency, medication dosage and number of follow-up visits in the prescription information includes: Calculate the ratio of the medication use times to the follow-up visit times to obtain the average medication use times; calculate the average of the average medication use times of all medication types for the same patient to obtain the medication frequency representation value of the patient's prescription information; The product of the average number of medication times and the medication dosage is calculated to obtain a medication characteristic value, and the sum of the medication characteristic values ​​of all medication types in the prescription information is calculated and positively correlated to obtain a medication characteristic representation value of the patient's prescription information.

[0006] Furthermore, the step of constructing a three-dimensional space according to the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value to obtain prescription characteristic points of different patients, and obtaining the average difference distance according to the distance characteristics between the prescription characteristic points includes: Taking the medication characteristic characterization value as the X-axis, the number of follow-up visits as the Y-axis, and the medication frequency characteristic value as the Z-axis, the prescription feature points are determined according to the positions of the medication characteristic characterization value, the number of follow-up visits, and the medication frequency characteristic value of each patient in the three-dimensional rectangular coordinate system; calculating the Euclidean distance between any two prescription feature points in the three-dimensional space to obtain the difference distance; calculating the average value of the difference distance to obtain the average difference distance of the patient's prescription feature points in the three-dimensional space.

[0007] Furthermore, the step of obtaining the adjustment coefficient according to the correlation characteristics between the medication characteristic representation values ​​includes: The absolute value of the difference between any two of the medication characteristic representation values ​​is calculated to obtain the medication characteristic difference value; the average value of the medication characteristic difference value is calculated and normalized to obtain the adjustment coefficient of the neighborhood radius.

[0008] Furthermore, the step of obtaining a basic neighborhood radius according to the average difference distance and the adjustment coefficient includes: The product of the adjustment coefficient and the average difference distance is calculated to obtain the basic neighborhood radius of the clustering algorithm.

[0009] Furthermore, the step of clustering the drug characteristic representation values ​​according to the basic neighborhood radius to obtain cluster clusters includes: Clustering is performed using a DBSCAN clustering algorithm according to the basic neighborhood radius and the prescription feature points in the three-dimensional space to obtain different clusters.

[0010] Furthermore, the step of obtaining the inter-cluster difference value according to the difference characteristics of the medication characteristic representation values ​​between the clustering clusters includes: Calculate the average value of the medication feature characterization value corresponding to the prescription feature point in the cluster to obtain the intra-cluster medication feature characterization mean; calculate the absolute value of the difference between the intra-cluster medication feature characterization means of any two clusters to obtain the inter-cluster difference value between the clusters.

[0011] Furthermore, the step of obtaining the heterogeneity between clusters according to the distance feature between clusters and the inter-cluster difference value comprises: The Euclidean distance between the centroids of any two clusters is calculated to obtain the cluster distance; the product of the cluster distance and the corresponding inter-cluster difference value is calculated and normalized to obtain the heterogeneity between the clusters.

[0012] Furthermore, the step of merging the clusters according to the heterogeneity to obtain an optimized cluster includes: The clusters whose heterogeneity is less than a preset heterogeneity threshold are merged until the heterogeneity between the merged clusters is not less than the preset heterogeneity threshold, and all the clusters after the merger are called optimized clusters.

[0013] Furthermore, the step of obtaining a compression level according to the quantity characteristics of the prescription feature points in the optimization cluster and compressing the prescription information includes: The ratio of the number of the prescription feature points to all prescription feature points in any optimized cluster is calculated and positively correlated to be mapped into a preset range to obtain the compression level of the optimized cluster; and the prescription information corresponding to the optimized cluster is compressed by the Deflate algorithm according to the compression level.

[0014] The present invention has the following beneficial effects: In an embodiment of the present invention, obtaining the medication frequency characteristic value and the medication characteristic representation value can reflect the degree of dependence of patients on drugs in different prescription information, and then the prescription feature points of different patients can be obtained by constructing a three-dimensional space through the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value. Constructing a three-dimensional space about prescription feature points can facilitate clustering. The average difference distance can reflect the distance characteristics between prescription feature points, and then the neighborhood radius in the cluster can be determined according to the average difference distance; obtaining the adjustment coefficient can determine the value of the basic neighborhood radius according to the difference characteristics of the medication characteristic representation value; based on the basic neighborhood radius, the clustering cluster of prescription feature points can be more accurately obtained through the clustering algorithm. Calculating the heterogeneity can reflect the difference characteristics between different clustering clusters and whether they can be merged; obtaining the optimized cluster can more accurately distinguish the difference characteristics between different prescription information, making the clustering result more accurate. Finally, the prescription information is compressed to different degrees according to the quantity characteristics of the prescription feature points in the optimized cluster, thereby improving the accuracy of the compression degree of different prescription information. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for intelligent management of hospital pharmacy prescription information provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a hospital pharmacy prescription information intelligent management method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the intelligent management method of hospital pharmacy prescription information provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a hospital pharmacy prescription information intelligent management method provided by an embodiment of the present invention, the method comprising the following steps: Step S1, obtaining the patient's prescription information, and obtaining the patient's medication frequency characteristic value and medication characteristic representation value according to the medication type, medication frequency, medication dosage and number of follow-up visits in the prescription information.

[0021] In an embodiment of the present invention, the implementation scenario is to compress and store the prescription information of hospital patients. First, the prescription information of all patients' visits is obtained. The prescription information includes the number of follow-up visits of the patient, the number of times different types of medication are used, and the dosage of each medication. It should be noted that because different drugs may be solid and liquid, the dosage of each medication is unified into milligrams; subsequently, all data in the prescription information are dimensioned. The obtained prescription information can reflect the medication characteristics of different patients. For example, the number of medications, dosages, types of medications, and the number of follow-up visits can be regarded as similar medication characteristics; therefore, when compressing and storing the prescription information of all patients, medications with similar characteristics can be grouped into one category and the compression level can be unified. Therefore, it is necessary to classify different prescription information. First, according to the type of medication, number of medications, dosages, and number of follow-up visits in the prescription information, the patient's medication frequency characteristic value and medication characteristic representation value are obtained.

[0022] Preferably, in one embodiment of the present invention, obtaining the medication frequency characteristic value and the medication characteristic characterization value includes: calculating the ratio of the number of medication times to the number of follow-up visits, obtaining the average number of medication times, the larger the value of the average number of medication times, the more serious the patient's dependence on the drug. Calculate the average of the average number of medication times of all medication types for the same patient to obtain the medication frequency characterization value of the patient's prescription information; the medication frequency characterization value can reflect the patient's overall dependence on different drugs. Calculate the product of the average number of medication times and the medication dosage to obtain the medication characteristic value, calculate the sum of the medication characteristic values ​​of all medication types in the prescription information and positively map them, and obtain the medication characteristic characterization value of the patient's prescription information; the larger the medication characteristic characterization value, the more serious the patient's condition may be, and the higher the dependence on the drug. It should be noted that the medication characteristic characterization value can only reflect the degree of dependence of different patients on the drug, which is convenient for subsequent classification, and cannot reflect the type of patient's condition; patients with more similar medication characteristic characterization values ​​have closer dependence on the drug, and the more similar the size of the prescription information is, they can be classified into one category for compression. The formula for obtaining the medication characteristic characterization value includes: In the formula, Represents the patient's medication characteristic value, Indicates the number of medications taken by the patient. Indicates the number of follow-up visits for this patient. Indicates The number of times the drug was used, Indicates The dosage of the drug, Indicates The average number of times a drug is used, Indicates The medication characteristic value of the drug; Represents an exponential function with a natural constant as its base.

[0023] Step S2, construct a three-dimensional space based on the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value to obtain the prescription characteristic points of different patients, obtain the average difference distance based on the distance characteristics between the prescription characteristic points; obtain the adjustment coefficient based on the correlation characteristics between the medication characteristic representation values; obtain the basic neighborhood radius of clustering based on the average difference distance and the adjustment coefficient.

[0024] After obtaining the patient's medication characteristic value, the prescription information of different patients can be clustered; the existing commonly used clustering algorithms include density clustering algorithms such as the DBSCAN clustering algorithm and the OPTICS clustering algorithm. These algorithms are all based on the density between different data points for clustering, and cluster data points with close distances into a cluster. It should be noted that in the embodiment of the present invention, the DBSCAN clustering algorithm with better clustering effect is used for analysis. In this algorithm, two hyperparameters, the neighborhood radius and the minimum number of samples, need to be set. The setting size of the neighborhood radius will affect the final clustering effect. If the neighborhood radius is too large, prescription information with large feature differences will be clustered into the same cluster. If the neighborhood radius is too small, prescription information with similar features will be clustered into different clusters, which will ultimately affect the compression efficiency and accuracy. Therefore, it is necessary to set the neighborhood radius according to the difference characteristics between different prescription information.

[0025] Furthermore, the DBSCAN clustering algorithm performs clustering based on the density of data points in space, so it is necessary to construct a three-dimensional space based on the characteristic values ​​of medication characteristics, the number of follow-up visits, and the characteristic values ​​of medication frequency to obtain the prescription feature points of different patients, and obtain the average difference distance based on the distance characteristics between the prescription feature points.

[0026] Preferably, in one embodiment of the present invention, obtaining prescription feature points and average difference distances includes: constructing a three-dimensional rectangular coordinate system according to the medication feature characterization value, the number of follow-up visits, and the medication frequency characteristic value; wherein the medication feature characterization value is the X-axis, the number of follow-up visits is the Y-axis, and the medication frequency characteristic value is the Z-axis; determining the prescription feature points according to the positions of the medication feature characterization value, the number of follow-up visits, and the medication frequency characteristic value of each patient in the three-dimensional rectangular coordinate system; the position of each prescription feature point can reflect the patient's dependence on the drug, and the closer the prescription feature points are, the closer the prescription information is. Calculate the Euclidean distance between any two prescription feature points in the three-dimensional space to obtain the difference distance; calculate the average value of the difference distance to obtain the average difference distance of the patient's prescription feature points in the three-dimensional space. The larger the average difference distance, the greater the difference in the characteristics of the prescription information between different patients, and the length of the neighborhood radius needs to be increased in the clustering process; when the average difference distance is smaller, it means that the difference in the characteristics of the prescription information between different patients is smaller, and a smaller neighborhood radius is required in the clustering process to ensure the clustering effect.

[0027] After obtaining the average difference distance, it is necessary to analyze the neighborhood radius in the DBSCAN clustering algorithm. The patient's medication feature representation value is calculated in step S1. The greater the difference between the medication feature representation values, the greater the feature difference of the prescription information, and the larger the neighborhood radius needs to be. Therefore, the adjustment coefficient can be obtained based on the correlation characteristics between the medication feature representation values.

[0028] Preferably, in one embodiment of the present invention, obtaining the adjustment coefficient includes: calculating the absolute value of the difference between any two medication feature representation values ​​to obtain the medication feature difference value; calculating the average value of the medication feature difference value and normalizing it to obtain the adjustment coefficient of the neighborhood radius; when the medication feature difference value is larger, the adjustment coefficient is larger, which means that the characteristic difference of the prescription information is larger, and a larger neighborhood radius is required to ensure the clustering effect; when the medication feature difference value is smaller, the adjustment coefficient is smaller, which means that the characteristic difference of the prescription information is smaller, and a smaller neighborhood radius is required to ensure the clustering effect.

[0029] Furthermore, after obtaining the average difference distance of the prescription feature points in the three-dimensional space and the adjustment coefficient of the neighborhood radius, the basic neighborhood radius can be obtained according to the average difference distance and the adjustment coefficient; preferably, the product of the adjustment coefficient and the average difference distance is calculated to obtain the basic neighborhood radius of the DBSCAN clustering algorithm. When the adjustment coefficient and the average difference distance are larger, it means that the overall distribution of the prescription feature points in the three-dimensional space is more discrete and the characteristic differences of the prescription information are larger, then the clustering neighborhood radius needs to be larger; when the adjustment coefficient and the average difference distance are smaller, it means that the overall distribution of the prescription feature points in the three-dimensional space is more dense and the characteristic differences of the prescription information are smaller, then the clustering neighborhood radius needs to be smaller. The formula for obtaining the basic neighborhood radius includes: In the formula, represents the basic neighborhood radius, represents the number of difference values ​​of medication characteristics, Indicates The difference value of medication characteristics, represents the normalization function, represents the adjustment coefficient of the neighborhood radius, represents the average difference distance.

[0030] Step S3, clustering the prescription feature points according to the basic neighborhood radius to obtain clusters; obtaining inter-cluster difference values ​​according to the difference characteristics of the medication feature representation values ​​between the clusters; obtaining the heterogeneity between the clusters according to the distance characteristics between the clusters and the inter-cluster difference values.

[0031] After obtaining the basic neighborhood radius in the DBSCAN clustering algorithm, the prescription feature points in the three-dimensional space can be clustered according to the basic neighborhood radius through the DBSCAN clustering algorithm to obtain different clustering clusters; it should be noted that the DBSCAN clustering algorithm belongs to the existing technology, and the specific clustering steps will not be repeated; the minimum number of samples is set to 10, and the implementer can determine it according to the implementation scenario.

[0032] After clustering, the prescription information corresponding to the prescription feature points in each cluster is relatively similar, and the degree of drug dependence of patients is similar; however, the clustering algorithm may misidentify non-spherical or other complex-shaped clusters during the clustering process, resulting in poor clustering effect. Therefore, it is necessary to analyze the difference characteristics between the obtained clusters, merge the clusters with smaller differences, and improve the compression accuracy; first, the inter-cluster difference value is obtained based on the difference characteristics of the medication feature representation values ​​between the clusters.

[0033] Preferably, in an embodiment of the present invention, obtaining the inter-cluster difference value includes: calculating the average value of the medication feature representation values ​​corresponding to the prescription feature points within the cluster to obtain the intra-cluster medication feature representation mean; calculating the absolute value of the difference between the intra-cluster medication feature representation means of any two clusters to obtain the inter-cluster difference value between the clusters. The larger the inter-cluster difference value between the two clusters, the greater the feature difference of the prescription information within the two clusters, and the obvious difference in the prescription information; the smaller the inter-cluster difference value between the two clusters, the smaller the feature difference of the prescription information within the two clusters, and the greater the probability of merging.

[0034] Furthermore, when the distance between two clusters is closer in three-dimensional space, the probability of merging clusters is greater, so the heterogeneity between clusters can be obtained according to the distance characteristics between clusters and the difference between clusters; preferably, obtaining the heterogeneity includes: calculating the Euclidean distance of the centroids between any two clusters to obtain the cluster spacing, the larger the cluster spacing is, the larger the distance between the two clusters is; conversely, when the cluster spacing is smaller, it means that the distance between the two clusters is smaller. Calculate the product of the cluster spacing and the corresponding cluster difference value and normalize them to obtain the heterogeneity between clusters; when the difference between clusters and the cluster spacing are smaller, it means that the distance between the two clusters is closer, and the feature difference of the prescription information in the two clusters is smaller, the heterogeneity is smaller, and the probability that the two clusters can be merged is greater; conversely, when the difference between clusters and the cluster spacing of the two clusters are larger, it means that the distance between the two clusters is farther, and the feature difference of the prescription information in the two clusters is greater, the heterogeneity is greater, and the probability that the two clusters can be merged is smaller.

[0035] Step S4, merging the clusters according to the heterogeneity to obtain an optimized cluster; obtaining a compression level according to the quantity characteristics of the prescription feature points in the optimized cluster and compressing the prescription information.

[0036] After obtaining the heterogeneity between different clusters, the clusters can be merged according to the heterogeneity to obtain optimized clusters, specifically including: merging clusters whose heterogeneity is less than the preset heterogeneity threshold, until the heterogeneity between the merged clusters is not less than the preset heterogeneity threshold, and all clusters after merging are called optimized clusters. In the embodiment of the present invention, the preset heterogeneity threshold is 0.3, which can be determined by the implementer according to the implementation scenario; and if the heterogeneity between the merged cluster and other clusters is different, it is necessary to continue merging until the heterogeneity between all the merged clusters is not less than the preset heterogeneity threshold, and the final clusters are all called optimized clusters; the characteristic differences of the prescription information between each optimized cluster are obvious.

[0037] After obtaining different optimization clusters, it is necessary to compress all prescription information to different degrees, so the compression level is obtained according to the quantity characteristics of the prescription feature points in the optimization cluster and the prescription information is compressed; preferably, in one embodiment of the present invention, obtaining the compression level and compressing the prescription information includes: calculating the ratio of the number of prescription feature points in any optimization cluster to the number of all prescription feature points and positively mapping them within a preset range, when the ratio is larger, it means that there are more corresponding prescription information in the optimization cluster, which means that this type of prescription information is common and does not need to be called frequently, so a larger compression level is required, and the greater the compression degree, when the ratio is smaller, it means that the The less corresponding prescription information in the optimization cluster, the more rare this type of prescription information is, so the compression level needs to be reduced; in the embodiment of the present invention, the preset range is 0 to 9, corresponding to the 10 compression levels of the Deflate algorithm. The larger the quantity ratio, the greater the compression level and the greater the compression level; the specific mapping step is to calculate the quantity ratio of all optimization clusters, and positively map the quantity ratio to ten integers from 0 to 9 to obtain the compression level of the optimization cluster; according to the compression level, the prescription information corresponding to the optimization cluster is compressed by the Deflate algorithm. It should be noted that the Deflate compression algorithm belongs to the prior art, and the specific compression steps will not be repeated. At this point, the prescription information of all patients is classified and compressed to different degrees according to the quantity characteristics of the optimization cluster, which improves the accuracy of the compression degree of the prescription information.

[0038] In summary, the embodiment of the present invention provides a method for intelligent management of prescription information in a hospital pharmacy; obtain the patient's medication frequency characteristic value and medication characteristic characterization value according to the patient's prescription information, and obtain the patient's prescription characteristic point; obtain the average difference distance according to the distance characteristics of the prescription characteristic points, and obtain the adjustment coefficient according to the relevant characteristics of the medication characteristic characterization value; obtain the basic neighborhood radius according to the average difference distance and the adjustment coefficient and perform clustering; obtain the heterogeneity and optimized cluster according to the medication characteristic characterization value of the cluster cluster and the distance characteristics of the cluster cluster; obtain the compression level according to the quantity characteristics of the prescription characteristic points in the optimized cluster and compress the prescription information. The present invention clusters and optimizes the clustering results according to the characteristics of the prescription information, and performs different degrees of compression according to the clustering results, thereby improving the accuracy of the compression degree of the prescription information.

[0039] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0040] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for intelligent management of prescription information in hospital pharmacies, characterized in that: The method comprises the following steps: Obtain the patient's prescription information, and obtain the patient's medication frequency characteristic value and medication characteristic representation value based on the medication type, medication frequency, medication dosage, and number of follow-up visits in the prescription information; Constructing a three-dimensional space according to the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value to obtain the prescription characteristic points of different patients, obtaining the average difference distance according to the distance characteristics between the prescription characteristic points; obtaining the adjustment coefficient according to the correlation characteristics between the medication characteristic representation values; obtaining the basic neighborhood radius of clustering according to the average difference distance and the adjustment coefficient; Clustering the prescription feature points according to the basic neighborhood radius to obtain clusters; obtaining inter-cluster difference values ​​according to the difference characteristics of the medication feature representation values ​​between clusters; obtaining the heterogeneity between clusters according to the distance characteristics between clusters and the inter-cluster difference values; Merging the clusters according to the heterogeneity to obtain an optimized cluster; obtaining a compression level according to the quantity characteristics of the prescription feature points in the optimized cluster and compressing the prescription information; The step of obtaining the patient's medication frequency characteristic value and medication characteristic representation value according to the medication type, medication frequency, medication dosage and number of follow-up visits in the prescription information includes: Calculate the ratio of the medication use times to the follow-up visit times to obtain the average medication use times; calculate the average of the average medication use times of all medication types for the same patient to obtain the medication frequency representation value of the patient's prescription information; The product of the average number of medication times and the medication dosage is calculated to obtain a medication characteristic value, and the sum of the medication characteristic values ​​of all medication types in the prescription information is calculated and positively correlated to obtain a medication characteristic representation value of the patient's prescription information.

2. A hospital pharmacy prescription information intelligent management method according to claim 1, characterized in that: The steps of constructing a three-dimensional space according to the medication characteristic representation value, the number of follow-up visits and the medication frequency characteristic value to obtain prescription characteristic points of different patients, and obtaining the average difference distance according to the distance characteristics between the prescription characteristic points include: Taking the medication characteristic characterization value as the X-axis, the number of follow-up visits as the Y-axis, and the medication frequency characteristic value as the Z-axis, the prescription feature points are determined according to the positions of the medication characteristic characterization value, the number of follow-up visits, and the medication frequency characteristic value of each patient in the three-dimensional rectangular coordinate system; calculating the Euclidean distance between any two prescription feature points in the three-dimensional space to obtain the difference distance; calculating the average value of the difference distance to obtain the average difference distance of the patient's prescription feature points in the three-dimensional space.

3. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of obtaining the adjustment coefficient according to the correlation characteristics between the medication characteristic representation values ​​comprises: The absolute value of the difference between any two of the medication characteristic representation values ​​is calculated to obtain the medication characteristic difference value; the average value of the medication characteristic difference value is calculated and normalized to obtain the adjustment coefficient of the neighborhood radius.

4. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of obtaining the basic neighborhood radius of clustering according to the average difference distance and the adjustment coefficient comprises: The product of the adjustment coefficient and the average difference distance is calculated to obtain the basic neighborhood radius of the clustering algorithm.

5. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of clustering the prescription feature points according to the basic neighborhood radius to obtain cluster clusters comprises: Clustering is performed using a DBSCAN clustering algorithm according to the basic neighborhood radius and the prescription feature points in the three-dimensional space to obtain different clusters.

6. The intelligent management method of hospital pharmacy prescription information according to claim 1, characterized in that: The step of obtaining the inter-cluster difference value according to the difference characteristics of the medication characteristic representation values ​​between the clusters comprises: Calculate the average value of the medication feature characterization value corresponding to the prescription feature point in the cluster to obtain the intra-cluster medication feature characterization mean; calculate the absolute value of the difference between the intra-cluster medication feature characterization means of any two clusters to obtain the inter-cluster difference value between the clusters.

7. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of obtaining the heterogeneity between clusters according to the distance feature between clusters and the inter-cluster difference value comprises: The Euclidean distance between the centroids of any two clusters is calculated to obtain the cluster distance; the product of the cluster distance and the corresponding inter-cluster difference value is calculated and normalized to obtain the heterogeneity between the clusters.

8. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of merging the clusters according to the heterogeneity to obtain an optimized cluster comprises: The clusters whose heterogeneity is less than a preset heterogeneity threshold are merged until the heterogeneity between the merged clusters is not less than the preset heterogeneity threshold, and all the clusters after the merger are called optimized clusters.

9. The intelligent management method for hospital pharmacy prescription information according to claim 1, characterized in that: The step of obtaining a compression level according to the quantity characteristics of the prescription feature points in the optimization cluster and compressing the prescription information comprises: The ratio of the number of the prescription feature points to all prescription feature points in any optimized cluster is calculated and positively correlated to be mapped into a preset range to obtain the compression level of the optimized cluster; and the prescription information corresponding to the optimized cluster is compressed by the Deflate algorithm according to the compression level.

Images