Medicine flow direction data cleaning method and system based on intelligent processing

Abstract

The invention relates to the technical field of medicine flow direction data processing, and discloses a medicine flow direction data cleaning method and system based on intelligent processing, and the system comprises a medicine flow direction information obtaining module, a medicine flow direction information cleaning module, and a medicine flow direction information cleaning output module. Intelligent matching of target medicine flow direction data cleaning tool types is carried out based on big data storage medicine flow direction data cleaning tool type information in combination with an intelligent recognition algorithm and target medicine flow direction data attribute feature text information, and refined and intelligent analysis of the target medicine flow direction data cleaning tool types is achieved. The medicine flow direction data cleaning quality is improved; according to the target medicine flow direction data cleaning tool type analysis parameters, data cleaning is autonomously and efficiently carried out on the target medicine flow direction collection data, and efficient and accurate operation of target medicine flow direction data cleaning operation is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of medicine flow data processing, and in particular to a medicine flow data cleaning method and system based on intelligent processing. Background Art

[0002] The analysis of pharmaceutical flow data can be completed by using data visualization tools, statistical analysis methods, machine learning models for data processing, etc. Among them, data cleaning and preprocessing are the basic steps of pharmaceutical flow data analysis. Cleaning and preprocessing include deleting duplicate data, processing missing values, standardizing data, etc. Through these steps, the quality and consistency of the data can be ensured, thereby improving the accuracy and reliability of the results of pharmaceutical data analysis. Users can achieve scientific and accurate analysis of pharmaceutical flow data by cleaning and preprocessing the pharmaceutical flow data, providing strong support for users to make pharmaceutical sales decisions; however, the existing pharmaceutical flow data cleaning process cannot achieve accurate and efficient search for the required pharmaceutical flow data, nor can it intelligently and accurately screen pharmaceutical flow data cleaning tools, which reduces the quality and efficiency of pharmaceutical flow data cleaning.

[0003] A Chinese invention patent with announcement number CN112148851B discloses a method for constructing a medical knowledge question-and-answer system based on a knowledge graph, which constructs a medical knowledge graph by collecting medical knowledge data and performing data cleaning and processing; collects natural language questions and converts them into semantic query graphs to search for answers to questions in the medical knowledge graph and outputs them visually, thereby improving the retrieval accuracy of medical knowledge answers; however, the above technical solution cannot scientifically and accurately match the required data cleaning tools based on the characteristic information of the collected medical knowledge data, thereby reducing the quality of the medical knowledge graph construction and the reliability of the medical knowledge question-and-answer system. Summary of the invention

[0004] 1. Technical issues to be resolved In order to solve the problem that the above-mentioned existing medicine flow data cleaning processing cannot realize accurate and efficient search for the required medicine flow data, and cannot intelligently and accurately screen medicine flow data cleaning tools, thereby reducing the quality and efficiency of medicine flow data cleaning, the above purpose is to accurately collect target medicine flow search feature text information, accurately identify medicine flow search keywords, accurately match medicine flow search database type, accurately collect target medicine flow data, collect target medicine flow data attribute feature information, scientifically match medicine flow data cleaning tool types, autonomously and efficiently execute medicine flow data cleaning operations, and visually output and display medicine flow data cleaning results.

[0005] (II) Technical solution The present invention is implemented by the following technical solution: a method for cleaning medicine flow data based on intelligent processing, the method comprising the following steps: S1. Collect target medicine flow search feature text data; S2, performing search keyword recognition processing on the target medicine flow information search feature text information according to the target medicine flow search feature text data and the medicine flow search keyword data, and generating target medicine flow search keyword recognition data; S3, performing database object matching processing required for target medicine flow information search based on the target medicine flow search keyword identification data and the medicine flow search database, and generating a target medicine flow search database; S4, performing target medicine flow information collection and processing based on the target medicine flow search feature text data and the target medicine flow search database to generate target medicine flow collection data; S5. Collecting target medicine flow data attribute feature text data and performing data cleaning tool type analysis processing on medicine flow data cleaning tool type data required for target medicine flow data cleaning, and generating target medicine flow data cleaning tool type analysis data; S6, performing target medicine flow data cleaning processing according to the target medicine flow data cleaning tool type analysis data and the target medicine flow collection data to generate target medicine flow cleaning data; S7. Construct the target medicine flow cleaning output data and execute the target medicine flow data cleaning result output feedback operation.

[0006] Preferably, the operation steps of collecting target medicine flow search feature text data are as follows: S11. Collect the search feature text information of the target pharmaceutical product flow required by the user end online through the data collection dialog box of the pharmaceutical flow management platform, and generate the search feature text data of the target pharmaceutical flow The target medicine flow search feature text data includes the name feature text data, specification feature text data, batch number feature text data, production date feature text data, expiration date feature text data, sales volume feature text data, selling price feature text data and manufacturer feature text data of the target medicine product flow search.

[0007] The present invention accurately collects target medicine flow search feature text information through a data collection dialog box, thereby achieving the effect of providing reliable data support for accurately identifying target medicine flow data search keywords.

[0008] Preferably, the search keyword recognition processing of the target medicine flow information search feature text information is performed based on the target medicine flow search feature text data and the medicine flow search keyword data, and the operation steps of generating the target medicine flow search keyword recognition data are as follows: S21. Establishing a data set of keywords for searching medicine flow , ;in Indicates The medicine flow search keyword data corresponding to the medicine flow search feature text information type, Indicates the maximum value of the number of drug flow search feature text information types, the drug flow search feature text information types indicate the search feature text information corresponding to different types of drug flow data, the drug flow search keyword data indicates the drug flow data search keywords corresponding to different types of drug flow search feature text information; the drug flow search keyword data includes the name keyword, specification keyword, batch number keyword, production date keyword, expiration date keyword, sales volume keyword, selling price keyword and manufacturer keyword for drug product flow data search; S22, using XGBoost algorithm to search for characteristic text data of the target medicine flow A data set of keywords related to the medical flow search Search keyword data related to the pharmaceutical flow Perform character matching of drug flow search feature text information to search for the target drug flow search feature text data Corresponding drug flow search keyword data , and construct a target medical flow search keyword recognition data set , ,in Indicates Target medical flow search keyword recognition data, Indicates Target medical flow search keyword identification data.

[0009] The present invention achieves the effect of improving the accuracy of medicine flow data search by scientifically presetting medicine flow search keywords combined with XGBoost algorithm and target medicine flow search feature text information to perform intelligent identification of target medicine flow search keywords.

[0010] Preferably, the operation steps of generating a target medicine flow search database are as follows: S31. Establish a database collection for drug flow search , ;in Indicates A drug flow search database, Indicates the maximum value of the number of types of medicine flow search databases, wherein the medicine flow search database represents a medicine flow data search database composed of different types of medicine flow search keyword feature identifiers; the medicine flow search database includes a Chinese basic medicine database, a domestic medicine database, a Chinese medical insurance database, a Chinese hospital database, a Chinese commercial database, a Chinese pharmacy database, and a Chinese medical institution database; S32, using an iterative deepening search algorithm to search the target medicine flow to the keyword identification data set Target medical flow search keyword identification data to Combined with the pharmaceutical flow search database Pharmaceutical flow search database Perform drug flow search keyword matching to search for the target drug flow search keyword identification data to Corresponding medical flow search database , and build a target medicine flow search database collection , ,in Indicates Targeted drug flow search database, Indicates A targeted drug flow search database.

[0011] The present invention performs intelligent screening of target medicine flow search database types by standardly setting a medicine flow search database combined with an iterative deepening search algorithm and target medicine flow search keywords, thereby realizing precise search of the target medicine flow search database based on data analysis, and achieving the effect of precise search of the target medicine flow search database based on data analysis.

[0012] Preferably, the target medicine flow information collection process is performed based on the target medicine flow search feature text data and the target medicine flow search database to generate the target medicine flow collection data in the following steps: S41, searching the target medicine flow feature text data Enter the target medicine flow search database set respectively Target drug flow search database to In the corresponding database search dialog box, the search and collection operation of the target medicine flow information is performed; S42, searching the database for the target medicine in step S41 to The corresponding database search collects the target medicine flow information and generates the target medicine flow collection data through data identification. The target medicine flow collection data includes EXCEL version target medicine flow data, web page version target medicine flow data, picture version target medicine flow data, WORD version target medicine flow data and PDF version target medicine flow data.

[0013] The present invention achieves the effect of autonomous and efficient search of target medicine flow data by efficiently and accurately collecting and processing target medicine flow information based on target medicine flow search feature text information and a target medicine flow search database.

[0014] Preferably, the steps of collecting the target medicine flow data attribute feature text data and performing data cleaning tool type analysis processing required for target medicine flow data cleaning with the medicine flow data cleaning tool type data to generate the target medicine flow data cleaning tool type analysis data are as follows: S51, using a bidirectional search algorithm to collect data on the target medicine flow The corresponding medical flow data attribute feature text information is searched and collected, and the target medical flow data attribute feature text data is generated , the target medicine flow direction data attribute feature text data includes file type attribute feature text data, file size attribute feature text data, occupied space attribute feature text data, and file version attribute feature text data of the target medicine flow direction data; S52. Establish a data set of medicine flow data cleaning tool types , ;in Indicates Types of data on medical flow data cleaning tools, Indicates the maximum number of types of medicine flow data cleaning tools, and the types of medicine flow data cleaning tools include PowerQuery, OpenRefine, TableauPrep and FineDataLink; the medicine flow data cleaning tool type data indicates setting the optimal medicine flow data cleaning tool type information for different types of medicine flow data attribute feature text information; S53: the target medicine flow data attribute feature text data Data collection related to the pharmaceutical flow data cleaning tool type Types of data on medical flow data cleaning tools described in Perform character matching on the attribute feature of the medicine flow data to search for the attribute feature text data of the target medicine flow data Corresponding data type of the medicine flow data cleaning tool , and construct a target medical flow data cleaning tool type analysis data set , execute and generate the target medicine flow data cleaning tool type analysis data set The specific operations are as follows: S531, parameter initialization: data cleaning tool searches for bat population size , maximum number of iterations T, objective function F, data cleaning tool search bat individuals In the medical flow data cleaning tool type data collection Searching for positions in space , ; and speed , sound wave frequency , sound wave loudness and frequency ; S532: In the medicine flow data cleaning tool type data collection Search for data cleaning tools in the search space Search for the best data cleaning tools in the bat population Search for individual bat locations , that is, the data cleaning tool searches for bat populations in the medical flow data cleaning tool type data collection Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of data of the pharmaceutical flow data cleaning tool The speed and position are updated according to the following formulas: , ,in Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The speed in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type Speed ​​in the search space; Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The position in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type Position in the search space; S533, generate a random number rand1, rand1 is a random number in the interval [0, 1]. When rand1> , select an optimal data cleaning tool to search for bat individuals in the optimal data cleaning tool search for bat individuals, that is, in the data set of the type of medical flow data cleaning tool Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of data of the pharmaceutical flow data cleaning tool The optimal data cleaning tool is used to search for bat individuals near the location of , , Generate a local solution, that is, in the data set of the type of medical flow data cleaning tool Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of data of the pharmaceutical flow data cleaning tool ,in Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The loudness of the sound waves in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The frequency in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The initial frequency in the search space; otherwise, according to the formula , , update the data cleaning tool to search for bat locations, that is, in the data collection of the type of medicine flow data cleaning tool Update the search space to search for the attribute feature text data related to the target medicine flow data Matching data of the pharmaceutical flow data cleaning tool type The location of Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The loudness of the sound waves in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the medical flow data cleaning tool type The frequency in the search space, Indicates value The random function of and is a constant and 0﹤ ﹤1, >0; S534, generate another random number rand2, rand2 is a random number on [0, 1]; when rand2< , and the fitness of the objective function F is better than the new solution in S533, that is, in the data set of the type of medical flow data cleaning tool Search the search space to find the attribute feature text data related to the target medicine flow data Matching data of the pharmaceutical flow data cleaning tool type The fitness is better than the type data of the medicine flow data cleaning tool matched in S533 , then accept the type data of the medical flow data cleaning tool In the medical flow data cleaning tool type data collection Search the position of the space and update the position. The position update formula is as follows: , and according to the formula , , synchronous adjustment and ;in Indicates that the data cleaning tool searches for individual bats In the medical flow data cleaning tool type data collection New positions in the search space, Indicates that the data cleaning tool searches for individual bats In the medical flow data cleaning tool type data collection The old position in the search space, It represents any number in the range [-1, 1]; S535, sort the fitness values ​​of all individuals in the bat population searched by the data cleaning tool, and find the current best , that is, in the data collection of the type of medical flow data cleaning tool Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of data of the pharmaceutical flow data cleaning tool location; S536, repeatedly executing S532 to S535, when the maximum number of iterations T is met, outputting the attribute feature text data of the target medicine flow data Matching data of the pharmaceutical flow data cleaning tool type ; S537: Outputting the attribute feature text data of the target medicine flow direction data in step S536 Matching data of the pharmaceutical flow data cleaning tool type , and construct a target medical flow data cleaning tool type analysis data set , ,in Indicates Target medical flow data cleaning tool type analysis data, Indicates Target pharmaceutical flow data cleaning tool type analysis data.

[0015] The present invention achieves the effect of refined and intelligent analysis of the target medicine flow data cleaning tool type by storing medicine flow data cleaning tool type information based on big data combined with a bat optimization algorithm and the collected target medicine flow data attribute feature text information.

[0016] Preferably, the target medicine flow data cleaning process is performed according to the target medicine flow data cleaning tool type analysis data and the target medicine flow collection data, and the operation steps of generating the target medicine flow cleaning data are as follows: S61, when the target medicine flow data cleaning tool type analysis data set When the generation is completed, the data set is analyzed according to the target medicine flow data cleaning tool type Target medical flow data cleaning tool type analysis data to The corresponding medicine flow data cleaning tool collects data on the target medicine flow Perform data cleaning operations according to the attribute characteristics of the drug flow data and generate the target drug flow cleaning data .

[0017] The present invention independently and efficiently cleans the target medicine flow data collected according to the target medicine flow data cleaning tool type analysis parameters, thereby achieving the effect of efficient and accurate operation of the target medicine flow data cleaning operation.

[0018] Preferably, the steps of constructing the target medicine flow cleaning output data and performing the target medicine flow data cleaning result output feedback operation are as follows: S71. Obtain the target medicine flow cleaning data And after data identification, the target medicine flow cleaning output data is constructed ; S72, cleaning and outputting the target medicine flow data The data is pushed to the medicine flow management platform through the Internet communication network and the medicine flow cleaning data is fed back and output using a display screen.

[0019] The present invention constructs the target medicine flow cleaning output data based on scientific data processing, and cooperates with the display screen to intuitively visualize the feedback output of the target medicine flow data cleaning result display operation, so as to achieve the effect of efficient collection of target medicine flow cleaning data and timely and accurate output feedback.

[0020] A medicine flow data cleaning system based on intelligent processing, used to implement the medicine flow data cleaning method based on intelligent processing, the system includes a medicine flow information acquisition module, a medicine flow information cleaning module, and a medicine flow information cleaning output module; The medicine flow information acquisition module includes a target medicine flow search feature information acquisition unit, a medicine flow search keyword storage unit, a target medicine flow search keyword identification unit, a medicine flow search database storage unit, a target medicine flow search database matching unit, and a target medicine flow data collection unit; The target medicine flow search feature information acquisition unit acquires target medicine flow search feature text data through a data acquisition dialog box; the medicine flow search keyword storage unit is used to store medicine flow search keyword data; the target medicine flow search keyword identification unit performs search keyword identification processing of target medicine flow information search feature text information based on the target medicine flow search feature text data and the medicine flow search keyword data, and generates target medicine flow search keyword identification data; the medicine flow search database storage unit is used to store a medicine flow search database; the target medicine flow search database matching unit performs database object matching processing required for target medicine flow information search based on the target medicine flow search keyword identification data and the medicine flow search database, and generates a target medicine flow search database; the target medicine flow data collection unit performs target medicine flow information collection processing based on the target medicine flow search feature text data and the target medicine flow search database, and generates target medicine flow collection data; The medicine flow information cleaning module includes a target medicine flow data attribute feature information collection unit, a medicine flow data cleaning tool storage unit, a target medicine flow data cleaning tool analysis unit, and a target medicine flow data cleaning operation execution unit; The target medicine flow data attribute feature information collection unit collects target medicine flow data attribute feature text data; the medicine flow data cleaning tool storage unit is used to store medicine flow data cleaning tool type data; the target medicine flow data cleaning tool analysis unit performs data cleaning tool type analysis processing required for target medicine flow data cleaning based on the target medicine flow data attribute feature text data and medicine flow data cleaning tool type data, and generates target medicine flow data cleaning tool type analysis data; the target medicine flow data cleaning operation execution unit performs target medicine flow data cleaning processing based on the target medicine flow data cleaning tool type analysis data and the target medicine flow collection data, and generates target medicine flow cleaning data; The medicine flow information cleaning and output module includes a medicine flow data cleaning result acquisition unit and a medicine flow data cleaning result output feedback unit; The medicine flow data cleaning result acquisition unit is used to construct target medicine flow cleaning output data; the medicine flow data cleaning result output feedback unit pushes the target medicine flow cleaning output data to the medicine flow management platform through the Internet communication network and combines with the display screen to perform the target medicine flow data cleaning result output feedback operation.

[0021] (III) Beneficial effects The present invention provides a method and system for cleaning medicine flow data based on intelligent processing. It has the following beneficial effects: 1. Accurately collect target medicine flow search feature text information through the data collection dialog box, and provide reliable data support for accurate identification of target medicine flow data search keywords; scientifically preset medicine flow search keywords combined with intelligent search algorithms and target medicine flow search feature text information to intelligently identify target medicine flow search keywords, thereby improving the accuracy of medicine flow data search; standardly set medicine flow search database combined with intelligent search algorithms and target medicine flow search keywords to intelligently screen the target medicine flow search database type, and realize accurate search of target medicine flow search database based on data analysis, thereby improving the efficiency and quality of medicine flow data search; efficiently and accurately collect and process target medicine flow information based on target medicine flow search feature text information and target medicine flow search database, thereby realizing autonomous and efficient search of target medicine flow data, and improving the intelligence and reliability of medicine flow data search.

[0022] 2. Accurately collect target medicine flow data attribute feature text information based on data attribute feature keywords to provide real data support for scientific matching of target medicine flow data cleaning tool types; intelligently match target medicine flow data cleaning tool types based on big data storage medicine flow data cleaning tool type information combined with intelligent recognition algorithm and target medicine flow data attribute feature text information to achieve refined and intelligent analysis of target medicine flow data cleaning tool types and improve the quality of medicine flow data cleaning; autonomously and efficiently clean the target medicine flow collection data based on the target medicine flow data cleaning tool type analysis parameters to achieve efficient and accurate operation of target medicine flow data cleaning operations.

[0023] 3. By scientifically constructing the target medicine flow cleaning output data based on data processing, and coordinating with the display screen to intuitively visualize the feedback output of the target medicine flow data cleaning results display operation, the target medicine flow cleaning data can be efficiently collected and the output feedback can be timely and accurately output, thereby improving the efficiency and accuracy of the medicine flow data cleaning feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a module of a medicine flow data cleaning system based on intelligent processing provided by the present invention; Figure 2 A flow chart of the method for cleaning medical flow data based on intelligent processing provided by the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The embodiments of the intelligent processing-based medicine flow data cleaning method and system are as follows: Embodiment 1: See also Figure 1 - Figure 2 , a method for cleaning medical flow data based on intelligent processing, the method comprising the following steps: S1. Collect target medicine flow search feature text data; S2, performing search keyword recognition processing on the target medicine flow information search feature text information according to the target medicine flow search feature text data and the medicine flow search keyword data, and generating target medicine flow search keyword recognition data; S3, performing database object matching processing required for target medicine flow information search based on the target medicine flow search keyword identification data and the medicine flow search database, and generating a target medicine flow search database; S4, collecting and processing target medicine flow information based on the target medicine flow search feature text data and the target medicine flow search database to generate target medicine flow collection data; S5. Collecting target medicine flow data attribute feature text data and performing data cleaning tool type analysis processing on medicine flow data cleaning tool type data required for target medicine flow data cleaning, and generating target medicine flow data cleaning tool type analysis data; S6, performing target medicine flow data cleaning processing according to the target medicine flow data cleaning tool type analysis data and target medicine flow collection data to generate target medicine flow cleaning data; S7. Construct the target medicine flow cleaning output data and execute the target medicine flow data cleaning result output feedback operation.

[0027] For further information, see Figure 1 - Figure 2 The steps for collecting target medicine flow search feature text data are as follows: S11. Collect the search feature text information of the target pharmaceutical product flow required by the user end online through the data collection dialog box of the pharmaceutical flow management platform, and generate the search feature text data of the target pharmaceutical flow The target medicine flow search feature text data includes the name feature text data, specification feature text data, batch number feature text data, production date feature text data, expiration date feature text data, sales volume feature text data, selling price feature text data and manufacturer feature text data of the target medicine product flow search.

[0028] The operation steps of performing search keyword recognition processing on the target medicine flow information search feature text information based on the target medicine flow search feature text data and the medicine flow search keyword data to generate the target medicine flow search keyword recognition data are as follows: S21. Establishing a data set of keywords for searching medicine flow , ;in Indicates The medicine flow search keyword data corresponding to the medicine flow search feature text information type, Indicates the maximum value of the number of drug flow search feature text information types, the drug flow search feature text information types indicate the search feature text information corresponding to different types of drug flow data, and the drug flow search keyword data indicate the drug flow data search keywords corresponding to different types of drug flow search feature text information; the drug flow search keyword data includes the name keyword, specification keyword, batch number keyword, production date keyword, expiration date keyword, sales volume keyword, selling price keyword and manufacturer keyword for drug product flow data search; S22. Use XGBoost algorithm to search for feature text data of target medicine flow Data collection of keywords for searching medical flow Search keyword data on medical flow Perform character matching on the drug flow search feature text information to search for the target drug flow search feature text data Corresponding pharmaceutical flow search keyword data , and construct a target medical flow search keyword recognition data set , ,in Indicates Target medical flow search keyword recognition data, Indicates Target medical flow search keyword identification data.

[0029] The operation steps of generating the target medicine flow search database are as follows: S31. Establish a database collection for drug flow search , ;in Indicates A drug flow search database, Indicates the maximum number of types of medicine flow search databases, where the medicine flow search databases represent medicine flow data search databases composed of different types of medicine flow search keyword feature identifiers; medicine flow search databases include China Basic Drug Database, Domestic Drug Database, China Medical Insurance Database, China Hospital Database, China Commercial Database, China Pharmacy Database, and China Medical Institution Database; S32, using iterative deepening search algorithm to search for target medicines to identify keyword data sets Targeted pharmaceutical flow search keyword recognition data to Combined with the medical flow search database Traditional Chinese Medicine Flow Search Database Perform drug flow search keyword matching to search for target drug flow search keyword identification data to Corresponding medicine flow search database , and build a target medicine flow search database collection , ,in Indicates Targeted drug flow search database, Indicates A targeted drug flow search database.

[0030] The operation steps for collecting and processing target medicine flow information based on the target medicine flow search feature text data and the target medicine flow search database to generate target medicine flow collection data are as follows: S41. Search the target medicine flow for feature text data Enter the target medicine flow search database set respectively Chinese target medicine flow search database to In the corresponding database search dialog box, the search and collection operation of the target medicine flow information is performed; S42, searching the database for the target medicine flow in step S41 to The corresponding database search collects the target medicine flow information and generates the target medicine flow collection data through data identification. The target medicine flow data collection includes EXCEL version of target medicine flow data, web version of target medicine flow data, picture version of target medicine flow data, WORD version of target medicine flow data and PDF version of target medicine flow data.

[0031] Through the target medicine flow search feature information collection unit, the target medicine flow search feature text information is accurately collected using the data collection dialog box, providing reliable data support for the accurate identification of the target medicine flow data search keywords; the medicine flow search keyword storage unit and the target medicine flow search keyword identification unit cooperate with each other, scientifically preset the medicine flow search keywords combined with the intelligent search algorithm and the target medicine flow search feature text information to perform intelligent identification of the target medicine flow search keywords, thereby improving the accuracy of the medicine flow data search; the medicine flow search database storage unit and the target medicine flow search database matching unit cooperate with each other, standardize the medicine flow search database combined with the intelligent search algorithm and the target medicine flow search keywords to perform intelligent screening of the target medicine flow search database type, realize accurate search of the target medicine flow search database based on data analysis, and improve the efficiency and quality of the medicine flow data search; the target medicine flow data collection unit efficiently and accurately collects and processes the target medicine flow information based on the target medicine flow search feature text information and the target medicine flow search database, realizes autonomous and efficient search of the target medicine flow data, and improves the intelligence and reliability of the medicine flow data search.

[0032] For further information, see Figure 1 - Figure 2 , collect the target medicine flow data attribute feature text data and perform the data cleaning tool type analysis and processing required for target medicine flow data cleaning with the medicine flow data cleaning tool type data, and generate the target medicine flow data cleaning tool type analysis data in the following steps: S51. Use a two-way search algorithm to collect data on the target medicine flow The corresponding medical flow data attribute feature text information is searched and collected, and the target medical flow data attribute feature text data is generated , the target medicine flow direction data attribute feature text data includes the file type attribute feature text data, the file size attribute feature text data, the occupied space attribute feature text data, and the file version attribute feature text data of the target medicine flow direction data; S52. Establish a data set of medicine flow data cleaning tool types , ;in Indicates Types of data on medical flow data cleaning tools, Indicates the maximum number of types of medicine flow data cleaning tools, which include PowerQuery, OpenRefine, TableauPrep and FineDataLink; the medicine flow data cleaning tool type data indicates the optimal medicine flow data cleaning tool type information for different types of medicine flow data attribute feature text information; S53, target medicine flow data attribute feature text data Data collection of medical flow data cleaning tool types Traditional Chinese medicine flow data cleaning tool type data Perform character matching on the attribute characteristics of medicine flow data to search for the attribute characteristics text data of the target medicine flow data Corresponding medical flow data cleaning tool type data , and construct a target medical flow data cleaning tool type analysis data set , execute and generate target medicine flow data cleaning tool type analysis data set The specific operations are as follows: S531, parameter initialization: data cleaning tool searches for bat population size , maximum number of iterations T, objective function F, data cleaning tool search bat individuals Data collection in the pharmaceutical flow data cleaning tool type Searching for positions in space , ; and speed , sound wave frequency , sound wave loudness and frequency ; S532, in the data collection of medical flow data cleaning tool type Search for data cleaning tools in the search space Search for the best data cleaning tools in the bat population Search for individual bat locations , that is, data cleaning tools search for bat populations in the medical flow data cleaning tool type data collection Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of medical flow data cleaning tool data The speed and position are updated according to the following formulas: , ,in Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The speed in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool Speed ​​in the search space; Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The position in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool Position in the search space; S533, generate a random number rand1, rand1 is a random number in the interval [0, 1]. When rand1> , select an optimal data cleaning tool to search for bat individuals in the best data cleaning tool search for bat individuals, that is, in the medical flow data cleaning tool type data set Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of medical flow data cleaning tool data The optimal data cleaning tool is used to search for bat individuals near the location of , , Generate a local solution, that is, in the medical flow data cleaning tool type data set Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of medical flow data cleaning tool data ,in Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The loudness of the sound waves in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The frequency in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The initial frequency in the search space; otherwise, according to the formula , , update the data cleaning tool to search for bat locations, that is, in the medical flow data cleaning tool type data set Update the search space to search for the attribute feature text data related to the target medicine flow data Matching medical flow data cleaning tool type data The location of Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The loudness of the sound waves in the search space, Indicates that the data cleaning tool searches for individual bats exist After the iteration, the data set of the type of medical flow data cleaning tool The frequency in the search space, Indicates value The random function of and is a constant and 0﹤ ﹤1, >0; S534, generate another random number rand2, rand2 is a random number on [0, 1]; when rand2< , and the fitness of the objective function F is better than the new solution in S533, that is, in the data set of the type of medical flow data cleaning tool Search the search space to find the attribute feature text data related to the target medicine flow data Matching medical flow data cleaning tool type data The fitness is better than the type data of medical flow data cleaning tool matched in S533 , then accept the data of the type of medical flow data cleaning tool Data collection in the pharmaceutical flow data cleaning tool type Search the position of the space and update the position. The position update formula is as follows: , and according to the formula , , synchronous adjustment and ;in Indicates that the data cleaning tool searches for individual bats Data collection in the pharmaceutical flow data cleaning tool type New positions in the search space, Indicates that the data cleaning tool searches for individual bats Data collection in the pharmaceutical flow data cleaning tool type The old position in the search space, It represents any number in the range [-1, 1]; S535, sort the fitness values ​​of all individuals in the bat population searched by the data cleaning tool, and find the current best , that is, in the data collection of medical flow data cleaning tool type Search the search space to find the attribute feature text data related to the target medicine flow data The most matching type of medical flow data cleaning tool data location; S536, repeat S532 to S535, when the maximum number of iterations T is met, output the attribute feature text data of the target medicine flow data Matching medical flow data cleaning tool type data ; S537: Output the attribute feature text data of the target medicine flow data in step S536 Matching medical flow data cleaning tool type data , and construct a target medical flow data cleaning tool type analysis data set , ,in Indicates Target medical flow data cleaning tool type analysis data, Indicates Target pharmaceutical flow data cleaning tool type analysis data.

[0033] According to the target medicine flow data cleaning tool type analysis data, target medicine flow collection data, target medicine flow data cleaning processing is performed, and the operation steps for generating target medicine flow cleaning data are as follows: S61, when the target medicine flow data cleaning tool type analysis data collection When the generation is completed, analyze the data set according to the target pharmaceutical flow data cleaning tool type Target pharmaceutical flow data cleaning tool type analysis data to The corresponding medicine flow data cleaning tool collects data on the target medicine flow Perform data cleaning operations according to the attribute characteristics of the drug flow data and generate the target drug flow cleaning data .

[0034] Through the target medicine flow data attribute feature information collection unit, the target medicine flow data attribute feature text information is accurately collected based on the data attribute feature keywords, providing real data support for the scientific matching of the target medicine flow data cleaning tool type; the medicine flow data cleaning tool storage unit and the target medicine flow data cleaning tool analysis unit cooperate with each other, based on the big data storage medicine flow data cleaning tool type information combined with the intelligent recognition algorithm and the target medicine flow data attribute feature text information to perform intelligent matching of the target medicine flow data cleaning tool type, realize the refined and intelligent analysis of the target medicine flow data cleaning tool type, and improve the quality of medicine flow data cleaning; the target medicine flow data cleaning operation execution unit performs data cleaning on the target medicine flow collection data autonomously and efficiently according to the target medicine flow data cleaning tool type analysis parameters, and realizes efficient and accurate operation of the target medicine flow data cleaning operation.

[0035] For further information, see Figure 1 - Figure 2 The steps for constructing the target medicine flow cleaning output data and executing the target medicine flow data cleaning result output feedback operation are as follows: S71. Obtain target medicine flow cleaning data And after data identification, the target medicine flow cleaning output data is constructed ; S72. Clean and output data of target medicine flow The data is pushed to the medicine flow management platform through the Internet communication network and the medicine flow cleaning data is fed back and output using a display screen.

[0036] Through the cooperation between the medicine flow data cleaning result acquisition unit and the medicine flow data cleaning result output feedback unit, the target medicine flow data cleaning output data is scientifically constructed based on data processing, and the display screen is used to intuitively visualize the feedback output of the target medicine flow data cleaning result display operation, so as to achieve efficient collection of the target medicine flow data cleaning and timely and accurate output feedback, thereby improving the efficiency and accuracy of the medicine flow data cleaning feedback.

[0037] Embodiment 2: See also Figure 1 - Figure 2 , a medicine flow data cleaning system based on intelligent processing, used to implement a medicine flow data cleaning method based on intelligent processing, the system includes a medicine flow information acquisition module, a medicine flow information cleaning module, and a medicine flow information cleaning output module; The medicine flow information acquisition module includes a target medicine flow search feature information acquisition unit, a medicine flow search keyword storage unit, a target medicine flow search keyword identification unit, a medicine flow search database storage unit, a target medicine flow search database matching unit, and a target medicine flow data collection unit; A target medicine flow search feature information collection unit collects target medicine flow search feature text data through a data collection dialog box; a medicine flow search keyword storage unit is used to store medicine flow search keyword data; a target medicine flow search keyword identification unit performs search keyword identification processing of target medicine flow information search feature text information based on target medicine flow search feature text data and medicine flow search keyword data, and generates target medicine flow search keyword identification data; a medicine flow search database storage unit is used to store a medicine flow search database; a target medicine flow search database matching unit performs database object matching processing required for target medicine flow information search based on target medicine flow search keyword identification data and medicine flow search database, and generates a target medicine flow search database; a target medicine flow data collection unit performs target medicine flow information collection processing based on target medicine flow search feature text data and target medicine flow search database, and generates target medicine flow collection data; The medicine flow information cleaning module includes a target medicine flow data attribute feature information collection unit, a medicine flow data cleaning tool storage unit, a target medicine flow data cleaning tool analysis unit, and a target medicine flow data cleaning operation execution unit; A target medicine flow data attribute feature information collection unit collects target medicine flow data attribute feature text data; a medicine flow data cleaning tool storage unit is used to store medicine flow data cleaning tool type data; a target medicine flow data cleaning tool analysis unit performs data cleaning tool type analysis processing required for target medicine flow data cleaning based on target medicine flow data attribute feature text data and medicine flow data cleaning tool type data, and generates target medicine flow data cleaning tool type analysis data; a target medicine flow data cleaning operation execution unit performs target medicine flow data cleaning processing based on target medicine flow data cleaning tool type analysis data and target medicine flow collection data, and generates target medicine flow cleaning data; The medicine flow information cleaning output module includes a medicine flow data cleaning result acquisition unit and a medicine flow data cleaning result output feedback unit; The medicine flow data cleaning result acquisition unit is used to construct the target medicine flow cleaning output data; the medicine flow data cleaning result output feedback unit pushes the target medicine flow cleaning output data to the medicine flow management platform through the Internet communication network and executes the target medicine flow data cleaning result output feedback operation in conjunction with the display screen.

[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for cleaning medical flow data based on intelligent processing, characterized in that: The method comprises the following steps: S1. Collect target medicine flow search feature text data; S2, performing search keyword recognition processing on the target medicine flow information search feature text information according to the target medicine flow search feature text data and the medicine flow search keyword data, and generating target medicine flow search keyword recognition data; S3, performing database object matching processing required for target medicine flow information search based on the target medicine flow search keyword identification data and the medicine flow search database, and generating a target medicine flow search database; S4, performing target medicine flow information collection and processing based on the target medicine flow search feature text data and the target medicine flow search database to generate target medicine flow collection data; S5. Collecting target medicine flow data attribute feature text data and performing data cleaning tool type analysis processing on medicine flow data cleaning tool type data required for target medicine flow data cleaning, and generating target medicine flow data cleaning tool type analysis data; S6, performing target medicine flow data cleaning processing according to the target medicine flow data cleaning tool type analysis data and the target medicine flow collection data to generate target medicine flow cleaning data; S7. Construct the target medicine flow cleaning output data and execute the target medicine flow data cleaning result output feedback operation.

2. The method for cleaning medicine flow data based on intelligent processing according to claim 1, characterized in that: The S1 comprises the following steps: S11. Collect the search feature text information of the target pharmaceutical product flow required by the user end online through the data collection dialog box of the pharmaceutical flow management platform, and generate the search feature text data of the target pharmaceutical flow .

3. The method for cleaning medicine flow data based on intelligent processing according to claim 2 is characterized in that: The S2 comprises the following steps: S21. Establishing a data set of keywords for searching medicine flow , ;in Indicates The medicine flow search keyword data corresponding to the medicine flow search feature text information type, Indicates the maximum number of types of feature text information for drug flow search; S22, using XGBoost algorithm to With the With the Perform character matching of the characteristic text information in the medical flow search to search for the The corresponding , and construct a target medical flow search keyword recognition data set , ,in Indicates Target medical flow search keyword recognition data, Indicates Target medical flow search keyword identification data.

4. The method for cleaning medicine flow data based on intelligent processing according to claim 3 is characterized by: The S3 comprises the following steps: S31. Establish a database collection for drug flow search , ;in Indicates A drug flow search database, Indicates the maximum value of the number of types of medicine flow search databases, wherein the medicine flow search database indicates a medicine flow data search database composed of different types of medicine flow search keyword feature identifiers; S32, using iterative deepening search algorithm to As stated in to With the As stated in Perform drug flow search keyword matching to search for the target drug flow search keyword identification data to Corresponding medical flow search database , and build a target medicine flow search database collection , ,in Indicates Targeted medicine flow search database, Indicates A targeted drug flow search database.

5. The method for cleaning medicine flow data based on intelligent processing according to claim 4 is characterized in that: The S4 comprises the following steps: S41, the Enter the As stated in to In the corresponding database search dialog box, the search and collection operation of the target medicine flow information is performed; S42, the step S41 to The corresponding database search collects the target medicine flow information and generates the target medicine flow collection data through data identification. .

6. The method for cleaning medicine flow data based on intelligent processing according to claim 5 is characterized in that: The S5 comprises the following steps: S51, using a bidirectional search algorithm to The corresponding medical flow data attribute feature text information is searched and collected, and the target medical flow data attribute feature text data is generated ; S52. Establish a data set of medicine flow data cleaning tool types , ;in Indicates Types of data on medical flow data cleaning tools, Indicates the maximum number of types of medicine flow data cleaning tools, wherein the medicine flow data cleaning tool type data indicates setting the optimal medicine flow data cleaning tool type information for different types of medicine flow data attribute feature text information; S53, the With the As stated in Perform a character match on the attribute characteristics of the medicine flow data to search for the The corresponding , and construct a target medical flow data cleaning tool type analysis data set , execute and generate the target medicine flow data cleaning tool type analysis data set The specific operations are as follows: S531, parameter initialization: data cleaning tool searches for bat population size , maximum number of iterations T, objective function F, data cleaning tool search bat individuals In the Searching for positions in space , ; and speed , sound wave frequency , sound wave loudness and frequency ; S532, in the Search for data cleaning tools in the search space Search for the best data cleaning tools in the bat population Search for individual bat locations , that is, the data cleaning tool searches for bat populations in the Search the search space for The best match for location; S533, generate a random number rand1, rand1 is a random number in the interval [0, 1]. When rand1> , select an optimal data cleaning tool to search for bat individuals in the optimal data cleaning tool search for bat individuals, that is, in the Search the search space for The best match for The optimal data cleaning tool is used to search for bat individuals and generate a local solution near the location of Search the search space for The best match for ; Update the data cleaning tool to search for bat locations, that is, The search space is updated to search for Matching the location; S534, generate another random number rand2, rand2 is a random number on [0, 1]; when rand2< , and at this time the fitness of the objective function F is better than the new solution in S533, that is, in the Search the search space for Matching the The fitness is better than that of the matching in S533 , then accept the In the Search the position of the space and update the position; S535, sort the fitness values ​​of all individuals in the bat population searched by the data cleaning tool, and find the current best , that is, in the Search the search space for The best match for location; S536, repeat S532 to S535, and when the maximum number of iterations T is met, output Matching the ; S537, output in step S536 and Matching the , and construct a target medical flow data cleaning tool type analysis data set , ,in Indicates Target medical flow data cleaning tool type analysis data, Indicates Target pharmaceutical flow data cleaning tool type analysis data.

7. The method for cleaning medicine flow data based on intelligent processing according to claim 6, characterized in that: The S6 comprises the following steps: S61, when the When the generation is complete, according to the As stated in to The corresponding medical flow data cleaning tool Perform data cleaning operations according to the attribute characteristics of the drug flow data and generate the target drug flow cleaning data .

8. The method for cleaning medicine flow data based on intelligent processing according to claim 7, characterized in that: The S7 comprises the following steps: S71, obtaining the And after data identification, the target medicine flow cleaning output data is constructed ; S72, the The data is pushed to the medicine flow management platform through the Internet communication network and the medicine flow cleaning data is fed back and output using a display screen.

9. A medicine flow data cleaning system based on intelligent processing, used to implement the medicine flow data cleaning method based on intelligent processing according to any one of claims 1 to 8, characterized in that: The system includes a medicine flow information acquisition module, a medicine flow information cleaning module, and a medicine flow information cleaning output module.

Images