CN117476165B - Intelligent management method and system for Chinese patent medicine medicinal materials - Google Patents
Intelligent management method and system for Chinese patent medicine medicinal materials Download PDFInfo
- Publication number
- CN117476165B CN117476165B CN202311800456.1A CN202311800456A CN117476165B CN 117476165 B CN117476165 B CN 117476165B CN 202311800456 A CN202311800456 A CN 202311800456A CN 117476165 B CN117476165 B CN 117476165B
- Authority
- CN
- China
- Prior art keywords
- cluster
- data
- data points
- split
- chinese patent
- 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.)
- Active
Links
- 239000003814 drug Substances 0.000 title claims abstract description 128
- 239000000463 material Substances 0.000 title claims abstract description 82
- 238000007726 management method Methods 0.000 title claims abstract description 41
- 229940079593 drug Drugs 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 102000003780 Clusterin Human genes 0.000 claims description 2
- 108090000197 Clusterin Proteins 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medicinal Chemistry (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The invention relates to the technical field of electronic digital data processing, in particular to an intelligent management method and system for Chinese patent medicine medicinal materials, comprising the following steps: and carrying out iterative splitting on the cluster formed by all the Chinese patent medicines through weighted distances, and carrying out unified management on the Chinese patent medicines in the final cluster. According to the invention, clustering and splitting are carried out by combining the weighted distances, so that the classification accuracy of Chinese patent medicines is improved, the Chinese patent medicines in the same clustering cluster can be uniformly managed by carrying out iterative splitting on the clustering clusters, the Chinese patent medicines under similar conditions are classified and stored, the searching and the storage are convenient, each Chinese patent medicine is ensured to be in good storage conditions, and the management efficiency of the Chinese patent medicine medicines is improved.
Description
Technical Field
The invention relates to the technical field of electronic digital data processing, in particular to an intelligent management method and system for Chinese patent medicine medicinal materials.
Background
Along with development and application of information technology, the intelligent management method and system of medicinal materials are widely applied in the Chinese patent medicine industry. The system realizes the full life cycle management of the medicinal materials by utilizing technologies such as the Internet of things, cloud computing, big data and the like. However, in the process of managing the Chinese patent medicine, the storage of different kinds of medicines by using different storage conditions is often not fully considered, so that the management of the Chinese patent medicine is disordered.
At present, in a method for managing Chinese patent medicine medicinal materials, chinese patent medicines are generally clustered and classified, and unified storage management is carried out on the same storage conditions.
However, in the actual clustering process, due to the clustering algorithmThe actual clustering effect can be influenced by the value and the dependence degree of the Chinese patent medicine medicinal materials on different storage conditions, so that the Chinese patent medicine under the same storage conditions can be possibly caused to be in different clusters, the management efficiency of the Chinese patent medicine medicinal materials is further caused to be low, and the quality safety of the medicinal materials is difficult to ensure.
Disclosure of Invention
The invention provides an intelligent management method and system for Chinese patent medicines and medicinal materials, which aim to solve the existing problems.
The invention relates to an intelligent management method and system for Chinese patent medicine medicinal materials, which adopts the following technical scheme:
the embodiment of the invention provides an intelligent management method for Chinese patent medicine medicinal materials, which comprises the following steps of:
acquiring medicinal material storage data of a medicament;
acquiring a cluster formed by data points corresponding to all medicines, wherein one data point corresponds to one medicine storage data, carrying out iterative splitting on the cluster, and acquiring a splittable coefficient of the cluster according to the distance between the data points in any cluster and the difference between the medicine storage data in the iterative splitting process;
obtaining a split cluster according to the size of the splittable coefficient, weighting the distances between any data points in the split cluster according to the differences among elements in a sequence formed by the data stored by any medicinal materials of all the data points in the split cluster to obtain weighted distances, and clustering the data points in the split cluster by combining the weighted distances to obtain sub-clusters of the split cluster;
and obtaining a final cluster after iterative splitting, and uniformly managing medicines corresponding to all data points in the same final cluster.
Further, the specific method for acquiring the cluster formed by all the data points corresponding to the medicines comprises the following steps:
taking any one of the stored medicines as one data point, wherein one data point corresponds to one multidimensional medicine storage data, and taking a set formed by the data points corresponding to all medicines as an initial cluster.
Further, in the iterative splitting process, the splitting coefficient of the cluster is obtained according to the distance between the data points in any cluster and the difference between the stored data of the medicinal materials, and the method comprises the following specific steps:
obtaining a local average distance of the data points and an overall distance parameter of the cluster according to the distance between the data points;
the method for calculating the splittable coefficients of the cluster comprises the following steps:
wherein,a splittable coefficient representing a cluster; />Representing the number of data points in the cluster; />Representing the->Local average distance of data points; />Representing the overall distance parameter of the cluster; />And->Respectively representing a maximum value function and a minimum value function; />The number of suitable range parameters representing the cluster; />Representing the->Suitable range parameters for the stored data sequence.
Further, the method for obtaining the local average distance of the data points and the overall distance parameter of the cluster according to the distance between the data points comprises the following specific steps:
the vector formed by the stored data of all medicinal materials of the medicament is recorded as the stored vector of the corresponding data point of the medicament in the cluster, the Euclidean distance between the stored vectors of the data points is recorded as the distance parameter between the data points, and the data points in the cluster and any one data point are recordedThe corresponding data points under the minimum distance parameter are recorded as local data points of the data points, wherein +.>Is a preset super parameter;
in any cluster, the average value of the distance parameters between the data points and all the corresponding local data points is recorded as the local average distance of the data points, and the average value of the local average distance of all the data points in any cluster is recorded as the integral distance parameter of the cluster.
Further, the method for storing the parameters of the proper range of the data sequence comprises the following specific steps:
and ordering the storage data of any medicinal material of all data points in any cluster from small to large to obtain a storage data sequence, and recording the range of the value corresponding to all elements in the storage data sequence as a suitable range parameter of the storage data sequence.
Further, the method for obtaining the split cluster according to the size of the splittable coefficient comprises the following specific steps:
obtaining a splittable coefficient of an initial cluster, wherein the obtaining method of the splittable coefficient of the initial cluster is the same as that of the splittable coefficient of the cluster;
recording the splittable coefficients of the initial cluster as initial splittable coefficientsWill->Let be the threshold value of the mitobility coefficient->Wherein->Is a preset splitting ratio;
when the coefficient of splittability of any clusterWhen the cluster is recorded as a split cluster.
Further, the method for weighting the distances between any data points in the split cluster to obtain weighted distances according to the differences between elements in a sequence formed by the storage data of any medicinal materials of all the data points in the split cluster comprises the following specific steps:
obtaining a data level of the data point according to the numerical value of the element in the stored data sequence and the proper range parameter of the stored data sequence;
the first data point of all data points in the split clusterIn the stored data sequence formed by the stored data of the individual medicinal materials, the first ∈>Person and->The data level difference of each element is recorded as a second value, and the +.>The accumulated values of all second numerical values in a stored data sequence formed by the stored data of the individual medicinal materials are recorded as the weight values of the stored data of the medicinal materials of all data points in the split cluster;
the specific calculation method of the weighted distance between the data points is as follows:
wherein,representing data points in split clusters->Data points->A weighted distance between; />A quantity of drug storage data representing data points; />Representing the +.>The weight of the data stored in each medicinal material; />Representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing an absolute value function;
and acquiring a weighted distance between any two data points in the split cluster, taking the two data points with the largest weighted distance as cluster centers, combining the weighted distances according to the two cluster centers in the split cluster, and acquiring sub-clusters of the split cluster by using a K-means clustering algorithm.
Further, the method for obtaining the data level of the data point according to the numerical value of the element in the stored data sequence and the parameter of the proper range of the stored data sequence comprises the following specific steps:
the number of data points contained in the split cluster and the first data point in the split clusterThe ratio of the parameters of the proper range of the stored data sequences is marked as a first value, and the +.>The first part of the stored data sequence>The ratio of the value of the element to the first value is recorded as +.>The first part of the stored data sequence>The individual elements correspond to the data levels of the data points.
Further, the iterative splitting of sub-clusters of all split clusters obtains a final cluster, and the unified management of the medicines corresponding to all data points in the same final cluster is carried out, which comprises the following specific steps:
according to the acquisition method of the sub-cluster, carrying out iterative splitting on all the clusters until the splittable coefficient of the cluster is smaller than the splittable coefficient threshold value, and obtaining a plurality of final clusters;
and carrying out storage management on the data points in the same final cluster corresponding to the Chinese patent medicines under the same condition.
The embodiment of the invention provides an intelligent management system for Chinese patent medicine medicinal materials, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the intelligent management methods for Chinese patent medicine medicinal materials when executing the computer program.
The technical scheme of the invention has the beneficial effects that: the multi-dimensional medicinal material storage data are utilized to classify Chinese patent medicines, and clustering splitting and weighting distance are adopted to carry out Chinese patent medicine management, so that classification accuracy of Chinese patent medicine is improved, unified management of Chinese patent medicines in the same cluster can be realized through iterative splitting of the cluster, classification storage of Chinese patent medicines under similar conditions is carried out, searching and storage are convenient, each Chinese patent medicine can be guaranteed to be in good storage conditions, and management efficiency of Chinese patent medicine medicinal materials is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of an intelligent management method of Chinese patent medicines.
Detailed Description
In order to further illustrate the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent management method and system for Chinese patent medicine according to the invention, which are provided by the invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a method and a system for intelligently managing Chinese patent medicine medicinal materials, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a step flow chart of a method for intelligently managing medicinal materials of a Chinese patent medicine according to an embodiment of the invention is shown, and the method comprises the following steps:
step S001: and obtaining medicinal material storage data of the medicament.
The Chinese patent medicines are classified by the data, and the Chinese patent medicines with similar storage conditions and similar components are classified and stored, so that the Chinese patent medicines can be stored under proper storage conditions while being more conveniently managed. According to the data, the most suitable storage conditions, main functions and the like of each type of Chinese patent medicine can be known according to the composition components of the Chinese patent medicine, and the Chinese patent medicine and medicinal materials are classified according to the characteristics.
Specifically, in order to implement the intelligent management method for the medicinal materials of the Chinese patent medicine provided in this embodiment, firstly, multidimensional medicinal material storage data of the medicine needs to be collected, and the specific process is as follows:
the method comprises the steps of obtaining the variety and the quantity of stored Chinese patent medicine medicinal materials, collecting data in the storage process of the Chinese patent medicine medicinal materials, and recording the data as multidimensional medicinal material storage data of the medicines, wherein the multidimensional medicinal material storage data comprise: the optimal temperature, the optimal humidity, the optimal illumination, the medicine components and the residual validity period of the medicine in the medicine storage process are collectively called as medicine storage data.
The method can be used for obtaining the variety and the number of the Chinese patent medicine medicinal materials and the multidimensional medicinal material storage data.
Step S002: and obtaining a cluster formed by data points corresponding to all medicines, wherein one data point corresponds to one medicine storage data, carrying out iterative splitting on the cluster, and obtaining the splittable coefficient of the cluster according to the distance between the data points in any cluster and the difference between the medicine storage data in the iterative splitting process.
It should be noted that, for each cluster in the clustering process, analysis can be performed according to the degree of dispersion of data points in the cluster, so that the local density difference of different data points in the cluster is larger and the multidimensional volume of the cluster is smaller.
Specifically, firstly, taking any one stored medicine as a data point, storing data corresponding to a multidimensional medicinal material by one data point, taking a set formed by data points corresponding to all medicines as a cluster, marking the cluster as an initial cluster, splitting the initial cluster to obtain a sub-cluster, and carrying out iterative splitting on the initial cluster and the sub-cluster, wherein the initial cluster and the sub-cluster are collectively called as a cluster.
Further, the vector formed by the stored data of all medicinal materials of the medicament is recorded as the stored vector of the corresponding data point of the medicament in the cluster, the Euclidean distance between the stored vectors of the data points is recorded as the distance parameter between the data points, and the distance between any one data point in the clusterThe corresponding data points under the minimum distance parameter are recorded as local data points of the data points, wherein +.>Is a preset super parameter.
It should be noted that the super parameters are preset according to experienceThe present embodiment is not particularly limited, and may be adjusted according to actual conditions.
And then, in any cluster, the average value of the distance parameters between the data points and all the corresponding local data points is recorded as the local average distance of the data points, and the average value of the local average distance of all the data points in any cluster is recorded as the overall distance parameter of the cluster.
It should be noted that, according to the local average distance of each data point, the local density of each data point may be obtained. The larger the local density difference between all data points in the same cluster indicates the more likely that the clusters contain data points belonging to different clusters.
And finally, sorting the storage data of any medicinal material of all data points in any cluster from small to large to obtain a storage data sequence, and marking the range corresponding to the numerical values of all elements in the storage data sequence as the suitable range parameter of the storage data sequence.
Further, the splittable coefficients of any cluster in the iterative splitting process are obtained, and the specific calculation method is as follows:
wherein,a splittable coefficient representing a cluster; />Representing the number of data points in the cluster; />Representing the->Local average distance of data points; />Representing clusters of clustersOverall distance parameters; />And->Respectively representing a maximum value function and a minimum value function; />The number of suitable range parameters representing the cluster; />Representing the->Suitable range parameters for the stored data sequence.
It should be noted that, before splitting is performed for the first time, all data forms a cluster, and the cluster must be split, so that the threshold value of the splittable coefficient is obtained by taking the splittable coefficient of the initial cluster as a standard.
It should be noted that the splitting ratio is empirically presetThe present embodiment is not particularly limited, and may be adjusted according to actual conditions.
Further, the splittable coefficients of the initial cluster are recorded as initial splittable coefficientsWill->Let be the threshold value of the mitobility coefficient->。
So far, the splittable coefficients of the cluster and the splittable coefficient threshold value are obtained through the method.
Step S003: obtaining a split cluster according to the size of the splittable coefficient, weighting distances among any data points in the split cluster according to differences among elements in a sequence formed by any medicinal material storage data of all data points in the split cluster to obtain weighted distances, and clustering the data points in the split cluster by combining the weighted distances to obtain a sub-cluster of the split cluster.
It should be noted that, splitting a cluster according to a cluster splitting coefficient, splitting a splittable cluster, where splitting should make the cluster split into two new clusters with smaller splitting coefficients as far as possible, so that local densities should be similar and data should be as poor as possible.
Specifically, step (1), first, when the splittable coefficients of any cluster areAnd when the clustering clusters are marked as split clustering clusters, presetting a K value of a K-means clustering algorithm, and clustering data points in the split clustering clusters by using the K-means clustering algorithm to obtain sub-clustering clusters of the K clustering clusters marked as the split clustering clusters.
It should be noted that, the K value of the K-means clustering algorithm is preset to be 2 according to experience, and may be adjusted according to actual situations, and the embodiment is not specifically limited.
It should be noted that, in order to select the most suitable cluster center to perform cluster splitting, it is ensured that the difference between sub-clusters obtained after splitting the cluster splitting is large, and when the K-means clustering algorithm is combined to cluster data points in the split cluster so as to implement cluster splitting, the euclidean distance between the data points is weighted.
It should be noted that, the storage conditions of the Chinese patent medicine and the components of the medicine have a larger relationship, and the Chinese patent medicine with similar components of the medicine have different requirements on different storage conditions, so the Euclidean distance can be weighted according to the distribution uniformity degree of each item of data of all data points in the split cluster, and the cluster center for splitting can be selected more accurately according to the influence of the components of the Chinese patent medicine on the storage environment.
It should be noted that, one data point corresponds to a plurality of medicinal material storage data, different medicinal material storage data of a plurality of data points form a plurality of different storage data sequences, and one data point corresponds to a plurality of storage data sequences.
It should be noted that, each data item is weighted according to the uniformity degree of different data items in the split cluster, and in the Chinese patent medicine data, if all corresponding data items in the split cluster are more non-uniform, it is indicated that different types of data points contained in the split cluster are greatly influenced by the item data, and classification can be performed according to the item data.
Then, the data level of the data points in any split cluster is obtained, and the specific calculation method comprises the following steps:
wherein,representing the +.>The first part of the stored data sequence>Data levels of the data points corresponding to the individual elements; />Representing the +.>The first part of the stored data sequence>The numerical value of the individual elements; />Representing the +.>Number of stored dataProper range parameters according to the sequence; />Representing the number of data points contained in the split cluster.
The data level of each data is compared with the average value of all differential values, so that the data level of each data in the split cluster of the Chinese patent medicine is fully represented, and the subsequent weight calculation is facilitated.
Step (2), firstly, obtaining weights of medicinal material storage data of all data points in any split cluster, wherein the specific calculation method comprises the following steps:
wherein,representing the +.>The weight of the data stored in each medicinal material; />Representing the +.f. of all data points in a split cluster>The first part of the stored data sequence formed by the stored data of the individual medicinal materials>Data levels of individual elements; />Representing the +.f. of all data points in a split cluster>The first part of the stored data sequence formed by the stored data of the individual medicinal materials>Data level of individual elements.
It should be noted that the number of the substrates,the difference of the data levels of adjacent elements in the stored data sequence is obtained to reflect the distribution uniformity degree of the stored data of the medicinal materials, and the difference of the data levels is multiplied, wherein the more the cumulative result is close to 1, the more uneven the data distribution is, the greater the influence of the stored data of the medicinal materials on splitting is, so that the weight given by the stored data of the medicinal materials is greater.
It should be noted that, the data points contained in the split cluster correspond to different types of Chinese patent medicines, and the sensitivity degree of the Chinese patent medicines with different medicine components to the stored data of different medicinal materials is different, so that the more uneven the data distribution of the stored data of the medicinal materials is, the better the split cluster can be split by increasing the weight of the stored data of the medicinal materials.
It should be noted that, the data points in the split cluster are different corresponding to the pharmaceutical ingredients of the Chinese patent medicines, and the difference of the requirements on the storage environment is large, so that the difference of the medicinal material storage data of different Chinese patent medicines is reflected according to the range and the distribution uniformity degree of the medicinal material storage data of all the data points in the split cluster, and the weight is obtained by utilizing the difference.
Then, in the clustering process of the data points in the clustering cluster, the specific calculation method of the weighted distance between the data points is as follows:
wherein,representing data points in split clusters->Data points->A weighted distance between; />A quantity of drug storage data representing data points; />Representing the +.>The weight of the data stored in each medicinal material; />Representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing an absolute value function.
It should be noted that, when the difference of storage environments required by the corresponding Chinese patent medicines of two data points in the split cluster is larger, the corresponding weighted distance is larger, and further, the probability that the two data points are clustered and divided into different clusters is larger, in order to divide the Chinese patent medicines with larger difference of the corresponding storage environments in the split cluster into different clusters, two data points with the farthest weighted distances in all data points in the split cluster are taken as cluster centers.
And finally, acquiring a weighted distance between any two data points in the split cluster, taking the two data points with the largest weighted distance as cluster centers, combining the weighted distances according to the two cluster centers in the split cluster, and acquiring sub-clusters of the split cluster by using a K-means clustering algorithm to acquire a plurality of clusters.
It should be noted that, after the cluster is split, there may be a problem that the number of data points included in the sub-cluster is too small or the distribution of the data points is similar, so that the sub-cluster needs to be processed.
Further, the number of data points in the sub-cluster obtained after the split cluster is obtained, when the number of data points in the sub-cluster is smaller than a number threshold, the sub-cluster is marked as a first cluster, the cluster corresponding to the cluster center closest to the cluster center weighted by the target sub-cluster is marked as a second cluster, the first cluster and the second cluster are combined to obtain a third cluster, and the split processing is carried out on the third cluster.
When the third cluster is split, the cluster center of the first cluster is no longer used as the cluster center when the third cluster is split.
So far, a plurality of cluster clusters are obtained through the method.
Step S004: and obtaining a final cluster after iterative splitting, and uniformly managing medicines corresponding to all data points in the same final cluster.
Specifically, first, performing iterative splitting on all clusters until the splittable coefficient of the cluster is smaller than a splittable coefficient threshold value, and obtaining a plurality of final clusters.
And then, storing the data points in the same final cluster corresponding to the Chinese patent medicines under the same condition.
The storage mode is used for storing the Chinese patent medicines together, so that not only can each Chinese patent medicine be ensured to be in a good storage condition, but also the Chinese patent medicines with similar content of each component can be stored in the same place, thereby being more convenient to search and store and realizing optimized storage.
Through the steps, the intelligent management of important medicinal materials is completed.
The invention provides an intelligent management system for Chinese patent medicine medicinal materials, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the intelligent management methods for Chinese patent medicine medicinal materials when executing the computer program.
The technical scheme of the invention has the beneficial effects that: the multi-dimensional medicinal material storage data are utilized to classify Chinese patent medicines, and clustering splitting and weighting distance are adopted to carry out Chinese patent medicine management, so that classification accuracy of Chinese patent medicine is improved, unified management of Chinese patent medicines in the same cluster can be realized through iterative splitting of the cluster, classification storage of Chinese patent medicines under similar conditions is carried out, searching and storage are convenient, each Chinese patent medicine can be guaranteed to be in good storage conditions, and management efficiency of Chinese patent medicine medicinal materials is improved.
The following examples were usedThe model is used only to represent the negative correlation and the result of the constraint model output is at +.>In the section, other models with the same purpose can be replaced in the implementation, and the embodiment only uses +.>The model is described as an example, without specific limitation, wherein +.>Refers to the input of the model.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. An intelligent management method for Chinese patent medicine medicinal materials is characterized by comprising the following steps:
acquiring medicinal material storage data of a medicament;
acquiring a cluster formed by data points corresponding to all medicines, wherein one data point corresponds to one medicine storage data, carrying out iterative splitting on the cluster, and acquiring a splittable coefficient of the cluster according to the distance between the data points in any cluster and the difference between the medicine storage data in the iterative splitting process;
obtaining a split cluster according to the size of the splittable coefficient, weighting the distances between any data points in the split cluster according to the differences among elements in a sequence formed by the data stored by any medicinal materials of all the data points in the split cluster to obtain weighted distances, and clustering the data points in the split cluster by combining the weighted distances to obtain sub-clusters of the split cluster;
iteratively splitting sub-clusters of all split clusters to obtain a final cluster, and uniformly managing medicines corresponding to all data points in the same final cluster;
according to the difference between the data points in any cluster and the stored data of medicinal materials in the iterative splitting process, the splitting coefficient of the cluster is obtained, and the method comprises the following specific steps:
obtaining a local average distance of the data points and an overall distance parameter of the cluster according to the distance between the data points;
the method for calculating the splittable coefficients of the cluster comprises the following steps:
；
wherein,a splittable coefficient representing a cluster; />Representing the number of data points in the cluster; />Representing the->Local average distance of data points; />Representing the overall distance parameter of the cluster; />And->Respectively representing a maximum value function and a minimum value function; />The number of suitable range parameters representing the cluster; />Representing the->Suitable range parameters for the stored data sequence.
2. The intelligent management method of Chinese patent medicine according to claim 1, wherein the step of obtaining clusters formed by all data points corresponding to medicine comprises the following specific steps:
taking any one of the stored medicines as one data point, wherein one data point corresponds to one multidimensional medicine storage data, and taking a set formed by the data points corresponding to all medicines as an initial cluster.
3. The intelligent management method of Chinese patent medicine according to claim 1, wherein the obtaining the local average distance of data points and the overall distance parameter of cluster according to the distance between data points comprises the following specific steps:
the vector formed by the stored data of all medicinal materials of the medicament is recorded as the stored vector of the corresponding data point of the medicament in the cluster, the Euclidean distance between the stored vectors of the data points is recorded as the distance parameter between the data points, and the data points in the cluster and any one data point are recordedThe corresponding data points under the minimum distance parameter are recorded as local data points of the data points, wherein +.>Is a preset super parameter;
in any cluster, the average value of the distance parameters between the data points and all the corresponding local data points is recorded as the local average distance of the data points, and the average value of the local average distance of all the data points in any cluster is recorded as the integral distance parameter of the cluster.
4. The intelligent management method of Chinese patent medicine medicinal materials according to claim 1, wherein the parameters in the proper range of the stored data sequence comprise the following specific methods:
and ordering the storage data of any medicinal material of all data points in any cluster from small to large to obtain a storage data sequence, and recording the range of the value corresponding to all elements in the storage data sequence as a suitable range parameter of the storage data sequence.
5. The intelligent management method of Chinese patent medicine medicinal materials according to claim 2, wherein the obtaining split cluster according to the size of the splittable coefficient comprises the following specific steps:
obtaining a splittable coefficient of an initial cluster, wherein the obtaining method of the splittable coefficient of the initial cluster is the same as that of the splittable coefficient of the cluster;
recording the splittable coefficients of the initial cluster as initial splittable coefficientsWill->Let be the threshold value of the mitobility coefficient->Wherein->Is a preset splitting ratio;
when the coefficient of splittability of any clusterWhen the cluster is recorded as a split cluster.
6. The intelligent management method of Chinese patent medicine according to claim 4, wherein the steps of weighting distances between any data points in the split cluster according to differences between elements in a sequence formed by any medicine storage data of all data points in the split cluster to obtain weighted distances comprise the following specific steps:
obtaining a data level of the data point according to the numerical value of the element in the stored data sequence and the proper range parameter of the stored data sequence;
the first data point of all data points in the split clusterIn the stored data sequence formed by the stored data of the individual medicinal materials, the first ∈>Person and->The data level difference of each element is recorded as a second value, and the +.>The accumulated values of all second numerical values in a stored data sequence formed by the stored data of the individual medicinal materials are recorded as the weight values of the stored data of the medicinal materials of all data points in the split cluster;
the specific calculation method of the weighted distance between the data points is as follows:
；
wherein,representing data points in split clusters->Data points->A weighted distance between; />A quantity of drug storage data representing data points; />Representing the +.>The weight of the data stored in each medicinal material;representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing data points in split clusters->Is>Storing the numerical value of the data of each medicinal material; />Representing an absolute value function;
and acquiring a weighted distance between any two data points in the split cluster, taking the two data points with the largest weighted distance as cluster centers, combining the weighted distances according to the two cluster centers in the split cluster, and acquiring sub-clusters of the split cluster by using a K-means clustering algorithm.
7. The intelligent management method of Chinese patent medicine according to claim 6, wherein the data level of the data point is obtained according to the numerical value of the element in the stored data sequence and the parameter in the proper range of the stored data sequence, and the specific method comprises the following steps:
the number of data points contained in the split cluster and the first data point in the split clusterThe ratio of the parameters of the proper range of the stored data sequences is marked as a first value, and the +.>The first part of the stored data sequence>Numerical value of each element and firstThe ratio of the values is marked as the +.>The first part of the stored data sequence>The individual elements correspond to the data levels of the data points.
8. The intelligent management method of Chinese patent medicine according to claim 5, wherein the iterative splitting of sub-clusters of all split clusters to obtain a final cluster, and the unified management of medicines corresponding to all data points in the same final cluster comprises the following specific steps:
according to the acquisition method of the sub-cluster, carrying out iterative splitting on all the clusters until the splittable coefficient of the cluster is smaller than the splittable coefficient threshold value, and obtaining a plurality of final clusters;
and carrying out storage management on the data points in the same final cluster corresponding to the Chinese patent medicines under the same condition.
9. A chinese patent drug material intelligent management system comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311800456.1A CN117476165B (en) | 2023-12-26 | 2023-12-26 | Intelligent management method and system for Chinese patent medicine medicinal materials |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311800456.1A CN117476165B (en) | 2023-12-26 | 2023-12-26 | Intelligent management method and system for Chinese patent medicine medicinal materials |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117476165A CN117476165A (en) | 2024-01-30 |
| CN117476165B true CN117476165B (en) | 2024-03-12 |
Family
ID=89639919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311800456.1A Active CN117476165B (en) | 2023-12-26 | 2023-12-26 | Intelligent management method and system for Chinese patent medicine medicinal materials |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117476165B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630510A (en) * | 2008-07-18 | 2010-01-20 | 上海摩波彼克半导体有限公司 | Quick codebook searching method for LSP coefficient quantization in AMR speech coding |
| CN105956318A (en) * | 2016-05-19 | 2016-09-21 | 上海电机学院 | Improved splitting H-K clustering method-based wind power plant fleet division method |
| CN110812241A (en) * | 2019-10-18 | 2020-02-21 | 平安科技（深圳）有限公司 | Medication reminding method based on time sequence clustering and related equipment |
| CN112232119A (en) * | 2020-09-09 | 2021-01-15 | 自然资源部第四地形测量队 | Remote sensing texture image segmentation method and device |
| CN112835798A (en) * | 2021-02-03 | 2021-05-25 | 广州虎牙科技有限公司 | Cluster learning method, test step clustering method and related device |
| CN113222027A (en) * | 2021-05-19 | 2021-08-06 | 哈尔滨理工大学 | Self-adaptive clustering center density peak value clustering algorithm based on weighted shared nearest neighbor |
| CN113807612A (en) * | 2021-10-13 | 2021-12-17 | 四川久远银海软件股份有限公司 | Prediction method and device based on mental scale data |
| CN114638301A (en) * | 2022-03-17 | 2022-06-17 | 哈尔滨理工大学 | Density peak value clustering algorithm based on density similarity |
| CN117216131A (en) * | 2023-11-07 | 2023-12-12 | 深圳市前海蛇口自贸区医院(深圳市南山区蛇口人民医院) | Traditional Chinese medicine data management system based on data retrieval |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8019766B2 (en) * | 2007-03-30 | 2011-09-13 | Amazon Technologies, Inc. | Processes for calculating item distances and performing item clustering |
| US10417653B2 (en) * | 2013-01-04 | 2019-09-17 | PlaceIQ, Inc. | Inferring consumer affinities based on shopping behaviors with unsupervised machine learning models |
-
2023
- 2023-12-26 CN CN202311800456.1A patent/CN117476165B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630510A (en) * | 2008-07-18 | 2010-01-20 | 上海摩波彼克半导体有限公司 | Quick codebook searching method for LSP coefficient quantization in AMR speech coding |
| CN105956318A (en) * | 2016-05-19 | 2016-09-21 | 上海电机学院 | Improved splitting H-K clustering method-based wind power plant fleet division method |
| CN110812241A (en) * | 2019-10-18 | 2020-02-21 | 平安科技（深圳）有限公司 | Medication reminding method based on time sequence clustering and related equipment |
| CN112232119A (en) * | 2020-09-09 | 2021-01-15 | 自然资源部第四地形测量队 | Remote sensing texture image segmentation method and device |
| CN112835798A (en) * | 2021-02-03 | 2021-05-25 | 广州虎牙科技有限公司 | Cluster learning method, test step clustering method and related device |
| CN113222027A (en) * | 2021-05-19 | 2021-08-06 | 哈尔滨理工大学 | Self-adaptive clustering center density peak value clustering algorithm based on weighted shared nearest neighbor |
| CN113807612A (en) * | 2021-10-13 | 2021-12-17 | 四川久远银海软件股份有限公司 | Prediction method and device based on mental scale data |
| CN114638301A (en) * | 2022-03-17 | 2022-06-17 | 哈尔滨理工大学 | Density peak value clustering algorithm based on density similarity |
| CN117216131A (en) * | 2023-11-07 | 2023-12-12 | 深圳市前海蛇口自贸区医院(深圳市南山区蛇口人民医院) | Traditional Chinese medicine data management system based on data retrieval |
Non-Patent Citations (7)
| Title |
|---|
| A new globally adaptive k-nearest neighbor classifier based on local mean optimization;Yujie Song;《Soft Computing 》;20201003;第25卷;2417-2431 * |
| Smoothing Weight Distance to Solve Euclidean Distance Measurement Problems in K-Nearest Neighbor Algorithm;Guruh Putro Dirgantoro;《2021 IEEE 5th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)》;20211230;294-298 * |
| WDRKNN: Weighted Distance Representation based Nearest Neighbor for Hyperspectral Remote Sensing Imagery Classification;WDRKNN: Weighted Distance Representation based Nearest Neighbor for Hyperspectral Remote Sensing Imagery Classification;《2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)》;20231123;1-6 * |
| 函数型数据的分裂转移式层次聚类算法;孟银凤;《山东大学学报》;20211206;第52卷(第1期);19-27 * |
| 基于模拟划分的SP-k-means-+算法;杨勇;《吉林大学学报(工学版)》;20201027;第51卷(第5期);1808-1816 * |
| 基于相似度均值的分类数据层次聚类分析算法;褚轲欣;《计算机技术与发展》;20221110;第32卷(第11期);154-163 * |
| 面向复杂数据的密度峰值聚类算法研究;徐晓;《中国博士学位论文全文数据库 (信息科技辑)》;20210501(第2期);I138-23 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117476165A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615014B (en) | KL divergence optimization-based 3D object data classification system and method | |
| Huang et al. | Naive Bayes classification algorithm based on small sample set | |
| CN104298713B (en) | A kind of picture retrieval method based on fuzzy clustering | |
| WO2022126810A1 (en) | Text clustering method | |
| CN107066555B (en) | On-line theme detection method for professional field | |
| CN105117407B (en) | A kind of image search method of the range direction histogram based on cluster | |
| CN111401300B (en) | Face clustering archiving method and device and storage medium | |
| EP2737432A1 (en) | Incremental image clustering | |
| CN107832456B (en) | Parallel KNN text classification method based on critical value data division | |
| CN109558533B (en) | Personalized content recommendation method and device based on multiple clustering | |
| CN113868366B (en) | Streaming data-oriented online cross-modal retrieval method and system | |
| Zhu et al. | Weighting scheme for image retrieval based on bag‐of‐visual‐words | |
| WO2021179631A1 (en) | Convolutional neural network model compression method, apparatus and device, and storage medium | |
| WO2023108995A1 (en) | Vector similarity calculation method and apparatus, device and storage medium | |
| CN112749281A (en) | Restful type Web service clustering method fusing service cooperation relationship | |
| CN104778281A (en) | Image index parallel construction method based on community analysis | |
| TW202217597A (en) | Image incremental clustering method, electronic equipment, computer storage medium thereof | |
| WO2019120007A1 (en) | Method and apparatus for predicting user gender, and electronic device | |
| CN112598128A (en) | Model training and online analysis processing method and device | |
| CN115129949A (en) | Vector range retrieval method, device, equipment, medium and program product | |
| Ergun | Segmentation of wood cell in cross-section using deep convolutional neural networks | |
| CN114330584A (en) | Data clustering method and device, storage medium and electronic equipment | |
| CN117476165B (en) | Intelligent management method and system for Chinese patent medicine medicinal materials | |
| CN110209895B (en) | Vector retrieval method, device and equipment | |
| Oussama et al. | A fast weighted multi-view Bayesian learning scheme with deep learning for text-based image retrieval from unlabeled galleries |
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 |