Precise medicine conversion system, electronic equipment and storage medium

Abstract

The invention discloses a medicine precise conversion system, electronic equipment and a storage medium, and relates to the technical field of medical data processing, the system comprises a multi-source data acquisition module used for interacting an HIS system and an EMR system to obtain basic information and personalized information of a target user; the medicine dosage conversion prototype matching module is used for matching in a medicine dosage conversion prototype library based on the basic information and the personalized information to obtain a target medicine dosage conversion prototype and outputting a target medicine dosage conversion scheme; and the user interaction module is used for screening verification information from the dynamic verification library and sending the verification information to a target user, and the target user obtains a target drug dose conversion scheme. The technical problems that in the prior art, medicine dose conversion is not accurate enough, system interactivity is poor and data management safety is insufficient are solved, and the technical effects that medicine dose conversion is accurate, and system interactivity and data management safety are improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a precise drug conversion system, electronic equipment and storage medium. Background Art

[0002] In the medical field, accurate conversion of drug dosages is crucial to the treatment effect and safety of patients. Traditional drug dosage conversion methods often rely on the experience of medical staff and simple calculation tools, which have many drawbacks. On the one hand, individual differences between different patients, such as age, weight, physical function, disease status, etc., make it difficult for a unified dosage standard to meet actual needs, which can easily lead to inaccurate dosage conversion, affecting treatment effects and even causing adverse reactions. On the other hand, existing systems have shortcomings in data acquisition and interaction, and are unable to comprehensively and accurately obtain basic and personalized information about patients. In addition, data interaction between systems is not smooth, and cannot provide sufficient support for drug dosage conversion. At the same time, in data management, there is a lack of effective storage and update mechanisms and security measures, and the integrity and security of data are difficult to guarantee.

[0003] Existing technologies have technical problems such as inaccurate drug dosage conversion, poor system interactivity, and insufficient data management security. Summary of the Invention

[0004] The present application provides a precise drug conversion system, electronic device and storage medium, which are used to solve the technical problems of the prior art such as inaccurate drug dosage conversion, poor system interactivity and insufficient data management security.

[0005] In view of the above problems, the present application provides a drug precision conversion system, electronic device and storage medium.

[0006] In a first aspect of the present application, a system for accurate drug conversion is provided, comprising:

[0007] A multi-source data acquisition module is used to interact with the HIS system and the EMR system to obtain the basic information and personalized information of the target user; a drug dose conversion prototype matching module is used to match the basic information and personalized information in the drug dose conversion prototype library to obtain the target drug dose conversion prototype, and output the target drug dose conversion scheme based on the target drug dose conversion prototype; a user interaction module is used to filter verification information from the dynamic verification library and send it to the target user, and the target user obtains the target drug dose conversion scheme based on the verification information.

[0008] The second aspect of the present application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor is used to execute a precise drug conversion system provided by the present application.

[0009] The third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is used to execute a precise drug conversion system provided by the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The multi-source data acquisition module interacts with the HIS and EMR systems to obtain the target user's basic and personalized information. The drug dose conversion prototype matching module matches the basic and personalized information within the drug dose conversion prototype library to obtain the target drug dose conversion prototype and output the target drug dose conversion solution based on the target drug dose conversion prototype. The user interaction module selects verification information from the dynamic verification library and sends it to the target user, who then obtains the target drug dose conversion solution based on the verification information. This achieves the technical effect of achieving accurate drug dose conversion and improving system interactivity and data management security. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of the structure of a precise drug conversion system provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0015] Description of the accompanying drawings: multi-source data acquisition module 10, drug dosage conversion prototype matching module 20, user interaction module 30, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION

[0016] This application provides a precise drug conversion system, electronic equipment and storage medium to solve the technical problems of the existing technology such as inaccurate drug dosage conversion, poor system interactivity and insufficient data management security.

[0017] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0018] Example 1, as Figure 1 As shown, the present application provides a drug accurate conversion system, the system comprising:

[0019] The multi-source data acquisition module 10 is used to interact with the HIS system and the EMR system to obtain the basic information and personalized information of the target user.

[0020] Specifically, the multi-source data acquisition module 10 undertakes the important task of data collection in the entire drug precision conversion system. It obtains the basic information and personalized information of the target user by interacting with the HIS (Hospital Information System) system and the EMR (Electronic Medical Record) system. The HIS system contains a wealth of patient medical data, such as the patient's name, gender, age, contact information and other basic identity information, as well as hospitalization number, treatment department, admission time and other diagnosis and treatment related information, which constitute the basic information part of the target user. The EMR system focuses on recording the patient's medical details, such as past disease diagnosis, treatment process, drug allergy history, family medical history and other personalized information, and also covers current symptom descriptions, examination and test results and other data closely related to the current condition. The multi-source data acquisition module 10 uses a specially developed data interface program, follows unified data interaction standards and security protocols, and establishes stable connections with the HIS system and EMR system respectively. It accurately filters out information corresponding to the target user from massive amounts of data, integrates and pre-processes it according to the established format, removes duplicate or erroneous data, ensures that the acquired information is accurate and complete, and provides reliable data support for subsequent drug dosage conversion work.

[0021] The drug dose conversion prototype matching module 20 is used to match the basic information and personalized information in the drug dose conversion prototype library to obtain a target drug dose conversion prototype, and output a target drug dose conversion scheme according to the target drug dose conversion prototype.

[0022] Specifically, the drug dose conversion prototype matching module 20 uses the target user's basic information and personalized information obtained by the multi-source data acquisition module as a basis to carry out precise matching in the drug dose conversion prototype library. This module first classifies and organizes detailed information such as the user's age, gender, weight, medical history, and allergy history, and extracts features to form specific data tags. Then, using a matching algorithm, these data tags are compared one by one with a large number of different types of drug dose conversion prototypes stored in the drug dose conversion prototype library. These prototypes are based on a large amount of clinical data, medical research results, and past successful cases, covering drug dose conversion rules for various diseases and patient characteristics. During the comparison process, multiple factors are comprehensively considered, such as the matching degree between disease type and severity, and the fit between the patient's physiological characteristics and the scope of application of the prototype. Through this meticulous matching and screening, the target drug dose conversion prototype that best suits the target user is determined. Finally, based on the calculation logic, formulas, and related parameters set by the selected target prototype and combined with the specific information of the target user, an accurate target drug dosage conversion plan is calculated and output. This plan clarifies key information such as the specific type of drug required by the patient, the exact dosage for each dose, the number of doses per day, and the possible course of treatment, providing scientific and accurate guidance for rational clinical drug use.

[0023] The user interaction module 30 is used to filter verification information from the dynamic verification library and send it to a target user, and the target user obtains a target drug dosage conversion plan based on the verification information.

[0024] Specifically, the user interaction module 30 is primarily responsible for selecting appropriate verification information from the dynamic verification library and delivering it to the target user, thereby assisting the user in obtaining a target dose conversion plan. The dynamic verification library stores a vast amount of continuously updated verification information, covering the characteristics of various medications, feedback data on different dosages in clinical applications, medication experience of patients with similar conditions, and medication reference information derived from big data analysis. The user interaction module 30 first applies a screening algorithm to randomly generate first verification information from the dynamic verification library based on factors such as the target user's basic information and past medication history. To prevent duplicate push of similar information from impacting verification results, the generated first verification information is compared with the target user's historical verification information set within a historical window for similarity. If the similarity between the first verification information and the historical verification information set is less than or equal to a preset similarity threshold, the information is identified as filtered verification information and sent to the target user. After receiving the filtered verification information, the target user can use this information to understand the potential risks, potential side effects, and differences between different medication methods of the drug dose conversion plan, thereby gaining a more comprehensive and in-depth understanding of the system's target dose conversion plan and enabling more accurate acquisition and application of the plan.

[0025] In one possible implementation, the drug dosage conversion prototype matching module 20 further includes:

[0026] The historical drug dosage conversion data set acquisition unit is used to acquire the historical drug dosage conversion data set and the corresponding historical user basic information-personalized information set.

[0027] The two-dimensional cluster analysis unit is used to perform two-dimensional cluster analysis on the historical user basic information-personalized information set to obtain K clustered historical user basic information-personalized information sets, where K is the number of categories after clustering and K is a positive integer.

[0028] The mapping clustering unit is used to perform mapping clustering on the historical drug dosage conversion data set based on the K clustered historical user basic information-personalized information sets to obtain K clustered historical drug dosage conversion data sets.

[0029] The drug dosage conversion prototype library acquisition unit is used to construct drug dosage conversion prototypes using the K clustered historical user basic information-personalized information sets and the K clustered historical drug dosage conversion data sets to obtain a drug dosage conversion prototype library.

[0030] Specifically, in the precise drug conversion system, obtaining a collection of historical drug dose conversion data and its corresponding collection of historical user basic information and personalized information is a fundamental step in building a prototype drug dose conversion library. The system collects data from various hospital databases, clinical research records, and past case files. Historical drug dose conversion data details the specific circumstances of past drug dose conversions for different patients, covering key information such as the type of drug, the dose adjustment process, and the final determined dose. Each piece of such data is closely linked to the historical user basic information and personalized information for a specific patient. Historical user basic information includes basic physiological characteristics such as the patient's age, gender, weight, and height, as well as contact information and appointment times. Personalized information includes the patient's past disease diagnosis results, treatment experience, allergy history, family medical history, and even personalized content such as the patient's lifestyle and special physical conditions. By integrating and sorting these data scattered across different data sources, the corresponding historical drug dosage conversion data are matched one-to-one with the historical user basic information - personalized information according to specific identifiers (such as the patient's unique number, etc.), thus forming two complete sets that can be used for subsequent analysis, providing rich data support for the subsequent precise analysis of drug dosage conversion rules under different user characteristics.

[0031] In the process of building a prototype library for drug dosage conversion, a key step is to perform a two-dimensional cluster analysis of historical user basic information and personalized information. The acquired historical user basic information and personalized information set are analyzed along two key dimensions. In the basic information dimension, the system focuses on physiological characteristics such as age, gender, weight, and height, as well as factors influencing medication use, such as occupation. In the personalized information dimension, the system considers the patient's medical history, treatment history, drug allergies, family history, and even lifestyle and physical conditions. Using specialized clustering algorithms, such as K-Means clustering, the system calculates the similarity between data points and groups user information with similar characteristics. This similarity calculation takes into account the weighting of information from different dimensions. For example, for certain diseases, a patient's medical history and allergy history may be given higher weighting. Through repeated iterative calculations and classification adjustments, all historical user information is ultimately divided into K clusters of historical user basic information and personalized information sets. K represents the number of categories after clustering. It is a positive integer that is pre-set based on data characteristics and analysis purposes or automatically determined during the algorithm operation. The user information within each cluster set has high similarity in these two dimensions, providing an orderly data grouping for the subsequent construction of a drug dosage conversion prototype based on these clusters.

[0032] After completing a two-dimensional cluster analysis of the historical user basic information and personalized information sets, resulting in K clustered historical user basic information and personalized information sets, the next step is to map and cluster the historical drug dosage conversion data sets based on these clustering results. The system establishes a correspondence between the clustered historical user basic information and personalized information sets and the historical drug dosage conversion data, as each piece of historical drug dosage conversion data corresponds to a piece of historical user basic information and personalized information. For each clustered historical user basic information and personalized information set, the system searches for all corresponding historical drug dosage conversion data. For example, if users in a cluster have similar age ranges, specific medical histories, and the same allergy history, the system will filter out the drug dosage conversion data corresponding to these users and group them together to form a new clustered historical drug dosage conversion data set. By sequentially processing the K clustered historical user basic information and personalized information sets in this manner, K clustered historical drug dosage conversion data sets can ultimately be obtained. Each clustered historical drug dose conversion data set corresponds to the corresponding clustered historical user basic information-personalized information set, reflecting the commonalities and rules of similar user groups in drug dose conversion, and providing accurate data support for the subsequent construction of drug dose conversion prototypes.

[0033] After completing cluster analysis of historical data, generating K clusters of historical user basic and personalized information sets and corresponding K clusters of historical drug dose conversion data sets, the system leverages a neural network model to initiate the crucial step of building a prototype library for drug dose conversion. For each cluster of historical user basic and personalized information sets, the system analyzes its unique combination of user characteristics, such as age range, specific medical history, and allergies. It also associates the corresponding cluster with its historical drug dose conversion data set. A dedicated neural network computational model is built for each cluster, capable of learning the complex, nonlinear relationship between that cluster's user characteristics and drug dose conversion. Using a large amount of training data—data from the cluster's historical drug dose conversion data set—the model continuously optimizes its parameters, such as adjusting the connection weights between neurons, thereby improving the accuracy and efficiency of the model's drug dose conversion for that user. For example, for a cluster of users with cardiovascular disease and similar physical characteristics, the neural network model analyzes their historical drug dose conversion data, including medication types, dose adjustments, and treatment response feedback, to learn a drug dose conversion model suitable for this user. After the neural network models for the K clusters are constructed, they together form a prototype library for drug dosage conversion. In practice, when a target user's basic and personalized information is input, the system can quickly match the corresponding cluster, invoke the corresponding neural network computational model, and accurately and efficiently generate a drug dosage conversion solution tailored to that user.

[0034] In one possible implementation, the two-dimensional cluster analysis unit further includes:

[0035] The user information random extraction subunit is used to randomly extract K leading historical user basic information-personalized information from the historical user basic information-personalized information set.

[0036] The information set clustering subunit is used to cluster the historical user basic information-personalized information set based on the K leading historical user basic information-personalized information according to a preset clustering rule to obtain K initial clustered historical user basic information-personalized information sets.

[0037] The cluster scoring subunit is used to use the cluster quality scoring function to perform overall cluster scoring on the K initial cluster historical user basic information-personalized information sets. When the scoring result is greater than or equal to a preset scoring threshold, the K cluster historical user basic information-personalized information sets are used as K cluster historical user basic information-personalized information sets.

[0038] Specifically, in the process of building the prototype library for drug dosage conversion, randomly extracting K leading historical user basic information and personalized information from the historical user basic information and personalized information set is a key operation. The historical user basic information and personalized information set contains a large amount of comprehensive information about different patients, such as age, gender, weight, medical history, allergy history, etc. The system uses a random number generation algorithm to ensure that each historical user basic information and personalized information has the same probability of being selected during the extraction process. After the random number is generated, it is used as an index to select the corresponding information from the historical user basic information and personalized information set. Each selection is independent and random, avoiding any biased selection. For example, if there are 1000 records in the historical user basic information - personalized information set, it is necessary to extract 5 (i.e. K = 5) leading historical user basic information - personalized information. The algorithm will randomly generate 5 different numbers in the range of 1 to 1000. According to the indexes corresponding to these numbers, 5 different historical user basic information - personalized information are accurately extracted from the set. These 5 pieces of information constitute K leading historical user basic information - personalized information, providing the starting key samples for subsequent clustering operations, so that the clustering process can more comprehensively and objectively reflect the characteristics of the data in the set.

[0039] During the construction of the prototype library for drug dosage conversion, the system clusters K randomly extracted historical user basic information and personalized information according to preset clustering rules, resulting in K initial clustered historical user basic information and personalized information sets. The preset clustering rules specify that each historical user basic information and personalized information set be assigned to the cluster corresponding to the leading historical user basic information and personalized information with the greatest similarity. The system then calculates the similarity between each piece of data in the historical user basic information and personalized information set and the K leading historical user basic information and personalized information. This similarity calculation takes into account several key factors, such as the user's age, gender, disease type, medical history, and allergy history. For age, similarity is measured by calculating the absolute value of the age difference and applying normalization. For disease type and medical history, quantitative assessment is performed by determining whether the disease is identical or similar, as well as the severity of the disease. Allergy history is calculated based on the overlap in the types of allergic medications. By performing weighted summation and other operations on these factors, a comprehensive similarity value is obtained. After calculating the similarity between the basic information and personalized information of all historical users and the basic information and personalized information of the K leading historical users, each historical user's basic information and personalized information is assigned to the cluster set corresponding to the leading historical user with the greatest similarity. For example, if the basic information and personalized information of a historical user have the greatest similarity with the basic information and personalized information of the third leading historical user among the K leading historical users, then the information of this historical user will be divided into the third cluster set. Similarly, after processing all the data in the historical user basic information and personalized information sets, K initial clustered historical user basic information and personalized information sets are finally formed. These initial cluster sets initially group together historical user information with similar characteristics, laying the foundation for further evaluation and optimization of clustering results and construction of a drug dosage conversion prototype.

[0040] In order to evaluate the quality of these K initial clusters, the system uses a special cluster quality scoring function to score the overall clustering. This scoring function takes into account multiple factors, such as the similarity of user information within the same cluster, the difference between different clusters, etc. For example, when calculating the similarity, different weights may be assigned according to the importance of different factors in affecting the drug dosage conversion, so as to more accurately measure the similarity between user information. When the scoring result is greater than or equal to the pre-set scoring threshold, it means that the current clustering effect is good and can effectively distinguish different types of user information. At this time, the system will determine these K initial clustering historical user basic information-personalized information sets as the final K clustering historical user basic information-personalized information sets, providing a reliable data grouping basis for the subsequent construction of the drug dosage conversion prototype library.

[0041] In one possible implementation, the cluster scoring subunit further includes:

[0042] The clustering quality scoring function obtains a micro-unit, which is used to obtain a clustering quality scoring function, wherein the clustering quality scoring function is:

[0043]

[0044] Among them, QC is the scoring result, n i is the amount of data in the i-th initial clustering historical user basic information-personalized information set among the K initial clustering historical user basic information-personalized information sets, is the basic information of the leading historical user in the basic information-personalized information of the i-th leading historical user corresponding to the basic information-personalized information set of the i-th initial clustering historical user, μ ij is the historical user basic information corresponding to the jth initial cluster historical user basic information-personalized information set in the i-th initial cluster historical user basic information-personalized information set, is the personalized information of the leading historical user in the basic information-personalized information of the i-th leading historical user corresponding to the basic information-personalized information set of the i-th initial clustering historical user, p ij is the historical user personalized information corresponding to the jth initial cluster historical user basic information-personalized information in the i-th initial cluster historical user basic information-personalized information set, is the similarity between the jth initial cluster historical user basic information-personalized information and the ith leading historical user basic information-personalized information in the i-th initial cluster historical user basic information-personalized information set.

[0045] Specifically, when constructing the drug dose conversion prototype library, the drug dose conversion prototype matching module needs to use the clustering quality scoring function to evaluate the clustering effect. First, a specific clustering quality scoring function must be obtained. In this formula, the final score of the QC table comprehensively reflects the quality of the clustering. K represents the number of cluster categories, n i It is the amount of data in the i-th initial cluster historical user basic information-personalized information set, reflecting the size of each cluster. is the basic information of the leading historical user corresponding to the i-th initial clustering historical user basic information-personalized information set, μ ij is the jth historical user basic information in the i-th initial clustering historical user basic information-personalized information set, through To measure the similarity between the basic information of the jth user in the i-th cluster and the basic information of the leading user in the cluster, the larger the ratio of the vector dot product to the vector modulus product, the higher the similarity. is the personalized information of the leading historical user corresponding to the i-th initial clustering historical user basic information-personalized information set, p ij is the jth historical user personalized information in the i-th initial clustered historical user basic information-personalized information set, What is calculated is the similarity between the two. The similarity is further mathematically transformed to more accurately evaluate the clustering effect. The module applies this scoring function to the K initial clustering historical user basic information-personalized information sets to calculate the overall clustering score QC. This scoring result is then compared with the preset scoring threshold. If the scoring result is greater than or equal to the preset scoring threshold, it means that the current clustering effect has reached the expected standard, the basic information and personalized information of the users within the cluster are highly similar, and the distinction between different clusters is also relatively reasonable, which can provide an effective data grouping basis for the subsequent construction of the drug dose conversion prototype. At this point, the current K clustering historical user basic information-personalized information sets can be used as the final effective clustering set for constructing the drug dose conversion prototype, ensuring the accuracy and reliability of the subsequent drug dose conversion scheme.

[0046] In one possible implementation, the user interaction module 30 further includes:

[0047] The historical verification information set acquisition unit is used to acquire the historical verification information set of the target user within the historical window.

[0048] The first verification information generating unit is configured to randomly generate first verification information from the dynamic verification library.

[0049] The first verification information judgment unit is used to judge whether the similarity between the first verification information and the historical verification information set is less than or equal to a preset similarity threshold; if so, the first verification information is used as the screening verification information.

[0050] Specifically, in the user interaction link of the drug precision conversion system, the system will first obtain the target user's historical verification information set within the historical window. This historical window can be set according to actual needs, such as the past week, month and other time periods. The system will filter out all the verification information received by the user within the historical window from the database that stores the verification information based on the target user's unique identifier (such as patient ID). This information covers various data from the previous verification of the user's drug dosage conversion plan, such as the recommended dosage range of different drugs, feedback on medication experience of similar cases, and drug side effect prompts.

[0051] The system randomly generates the first verification information from the dynamic verification library. This is a continuously updated database that stores a vast amount of verification information derived from clinical research findings, medication feedback from a large number of patients, and the experience of medical experts. Using a random algorithm, the system extracts a piece of information from this vast database as the first verification information, ensuring that each generated verification information is random and avoids duplication and limitations.

[0052] In this precise drug conversion system, the cosine similarity algorithm can be used to determine the similarity between the first verification information and the historical verification information set. First, each piece of information in the first verification information and the historical verification information set is converted into a vector form. For example, key elements such as the type of drug, dosage, applicable symptoms, and contraindications in the information are digitally encoded into vectors. Assume that the first verification information is processed into a vector A = [a1, a2, a3, ...], and a piece of information in the historical verification information set is processed into a vector B = [b1, b2, b3, ...]. According to the cosine similarity formula Calculate the similarity between the first verification information vector A and each information vector B in the historical verification information set. Wherein, A·B is the dot product of vectors A and B, and ‖A‖ and ‖B‖ are the moduli of vectors A and B respectively. Then, set a preset similarity threshold, such as 0.6. Compare each calculated similarity value with the preset threshold. If the similarity calculated between the first verification information and all information vectors in the historical verification information set is less than or equal to the preset threshold, it means that the similarity between the first verification information and the historical verification information set meets the requirements. At this time, the first verification information can be used as screening verification information to assist the target user in obtaining the target drug dosage conversion plan; if there is a situation greater than the preset threshold, it means that the first verification information has a high similarity with some information in the historical verification information set, and the verification information needs to be regenerated.

[0053] In one possible implementation, the first verification information determination unit further includes:

[0054] The verification information regeneration instruction acquisition subunit is used to acquire a verification information regeneration instruction if the similarity between the first verification information and the historical verification information set is greater than a preset similarity threshold, and regenerate the verification information based on the verification information regeneration instruction.

[0055] Specifically, in the user interaction module of the precise drug conversion system, after the system completes the generation of the first verification information and calculates its similarity with the historical verification information set, if the similarity between the first verification information and the historical verification information set is greater than a preset similarity threshold, the process of regenerating the verification information is triggered. The system first obtains a verification information regeneration instruction and activates the relevant program in the system responsible for generating the verification information. Based on this instruction, the system will randomly extract information from the dynamic verification library again. Because the information in the dynamic verification library is constantly updated and rich and diverse, the newly extracted information is likely to be different from the previous first verification information. The system regenerates the verification information and recalculates the similarity between the newly generated information and the historical verification information set until the similarity between the newly generated verification information and the historical verification information set is less than or equal to the preset similarity threshold. At this time, the regeneration process will be stopped and the verification information that meets the requirements will be sent to the target user as the selected verification information. This ensures that the verification information provided to the user is both valuable for reference and avoids excessive duplication with historical verification information, thus ensuring the accuracy and reliability of the drug dosage conversion plan.

[0056] In one possible implementation, the system further includes:

[0057] The scheme feedback module is used to collect the feedback information of the target user in a preset feedback window, and optimize the target drug dosage conversion scheme based on the feedback information to obtain an optimized drug dosage conversion scheme.

[0058] Specifically, the scheme feedback module is used to optimize the target drug dosage conversion scheme. After the target user uses the target drug dosage conversion scheme for drug treatment, the scheme feedback module begins to collect user feedback information within the preset feedback window. This preset feedback window can be a specific time point during the treatment process, or it can be after completing a treatment cycle. Feedback information covers multiple aspects, including the effectiveness of drug treatment, such as whether symptoms are relieved and whether disease indicators are improved; problems encountered during medication, such as whether there are side effects and whether the drug is convenient to take; and the user's own feelings about the drug dosage, such as whether the dosage is appropriate and whether it needs to be adjusted.

[0059] After receiving this feedback, the solution feedback module analyzes and processes it. It compares and correlates the feedback with existing drug knowledge and historical case data in the system. If the feedback indicates that expectations have not been met, the module will investigate various factors, such as inaccurate dosage calculations and inadequate consideration of individual user differences. Based on the analysis results, the module makes targeted adjustments to the target drug dosage conversion plan, such as changing the dosage and adjusting the frequency of medication. This optimizes the drug dosage conversion plan, making subsequent drug treatment more accurate and effective, and better meeting the treatment needs of the target user.

[0060] In one possible implementation, the system further includes:

[0061] The data storage and update module is used to communicate with the cloud database to update and store data, as well as to store and back up the received data.

[0062] Specifically, the data storage update module establishes a stable communication connection between the system and the cloud database, ensuring smooth data transmission between the system and the cloud. During system operation, both the target user's basic and personalized information acquired by the multi-source data acquisition module and various data generated during the drug dosage conversion process, such as historical drug dosage conversion data and cluster analysis results, are transmitted to the data storage update module. This module stores this data locally and categorizes and stores it according to data structure and storage rules, facilitating subsequent rapid retrieval and access. Furthermore, it synchronizes and updates this data to the cloud database, ensuring the real-time and integrity of cloud data. Furthermore, the data storage update module also undertakes the important task of data backup. Through a regular backup mechanism, critical data is stored in multiple different storage locations to prevent data corruption or loss due to hardware failure, data loss, or other unexpected situations. This enables the system to recover from backup data in the event of any issues, ensuring the continued stable operation of the precise drug conversion system and providing reliable data support for drug dosage conversion and other functions.

[0063] Example 2: Based on the same inventive concept as the drug accurate conversion system in the previous example, this example provides an electronic device. Figure 2 This is a structural diagram of an electronic device provided in accordance with the second embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present invention. Figure 2 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 2 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 2 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 2 The bus connection is taken as an example.

[0064] Example 3. Based on the same inventive concept as the precise drug conversion system described in the previous example, this example provides a computer-readable storage medium that can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the precise drug conversion system described in the example of this application. The processor executes the software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the computer device, thereby implementing the precise drug conversion system described above.

[0065] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0067] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A precise drug conversion system, characterized in that: The system comprises: Multi-source data acquisition module, used to interact with HIS system and EMR system to obtain basic information and personalized information of target users; a drug dose conversion prototype matching module, configured to perform matching in a drug dose conversion prototype library based on the basic information and the personalized information, obtain a target drug dose conversion prototype, and output a target drug dose conversion scheme based on the target drug dose conversion prototype; The user interaction module is used to filter verification information from the dynamic verification library and send it to the target user, and the target user obtains the target drug dosage conversion plan based on the verification information.

2. A drug accurate conversion system according to claim 1, characterized in that: The drug dosage conversion prototype matching module also includes: A historical drug dosage conversion data set acquisition unit, used to acquire a historical drug dosage conversion data set and a corresponding historical user basic information-personalized information set; a two-dimensional cluster analysis unit, configured to perform a two-dimensional cluster analysis on the historical user basic information-personalized information set to obtain K clustered historical user basic information-personalized information sets, where K is the number of clustered categories and is a positive integer; a mapping clustering unit, configured to perform mapping clustering on the historical drug dosage conversion data set based on the K clustered historical user basic information-personalized information sets to obtain K clustered historical drug dosage conversion data sets; The drug dosage conversion prototype library acquisition unit is used to construct drug dosage conversion prototypes using the K clustered historical user basic information-personalized information sets and the K clustered historical drug dosage conversion data sets to obtain a drug dosage conversion prototype library.

3. A drug accurate conversion system according to claim 2, characterized in that: The two-dimensional cluster analysis unit further includes: A user information random extraction subunit is used to randomly extract K leading historical user basic information-personalized information from the historical user basic information-personalized information set; An information set clustering subunit, configured to cluster the historical user basic information-personalized information set based on the K leading historical user basic information-personalized information according to a preset clustering rule to obtain K initial clustered historical user basic information-personalized information sets; The cluster scoring subunit is used to use the cluster quality scoring function to perform overall cluster scoring on the K initial cluster historical user basic information-personalized information sets. When the scoring result is greater than or equal to a preset scoring threshold, the K cluster historical user basic information-personalized information sets are used as K cluster historical user basic information-personalized information sets.

4. A drug accurate conversion system according to claim 3, characterized in that: The cluster scoring subunit further includes: The clustering quality scoring function obtains a micro-unit, which is used to obtain a clustering quality scoring function, wherein the clustering quality scoring function is: Among them, QC is the scoring result, n i is the amount of data in the i-th initial clustering historical user basic information-personalized information set among the K initial clustering historical user basic information-personalized information sets, is the basic information of the leading historical user in the i-th leading historical user basic information-personalized information corresponding to the i-th initial clustering historical user basic information-personalized information set, μ ij is the historical user basic information corresponding to the jth initial cluster historical user basic information-personalized information set in the i-th initial cluster historical user basic information-personalized information set, is the personalized information of the leading historical user in the basic information-personalized information of the i-th leading historical user corresponding to the basic information-personalized information set of the i-th initial clustering historical user, p ij is the historical user personalized information corresponding to the jth initial cluster historical user basic information-personalized information in the i-th initial cluster historical user basic information-personalized information set, is the similarity between the jth initial cluster historical user basic information-personalized information and the ith leading historical user basic information-personalized information in the i-th initial cluster historical user basic information-personalized information set.

5. The precise drug conversion system according to claim 1, characterized in that: The user interaction module also includes: A historical verification information set acquisition unit, configured to acquire the historical verification information set of the target user within a historical window; A first verification information generating unit, configured to randomly generate first verification information from the dynamic verification library; The first verification information judgment unit is used to judge whether the similarity between the first verification information and the historical verification information set is less than or equal to a preset similarity threshold; if so, the first verification information is used as the screening verification information.

6. A drug accurate conversion system according to claim 5, characterized in that: The first verification information determination unit further includes: The verification information regeneration instruction acquisition subunit is used to acquire a verification information regeneration instruction if the similarity between the first verification information and the historical verification information set is greater than a preset similarity threshold, and regenerate the verification information based on the verification information regeneration instruction.

7. The precise drug conversion system according to claim 1, characterized in that: Also includes: The scheme feedback module is used to collect the feedback information of the target user in a preset feedback window, and optimize the target drug dosage conversion scheme based on the feedback information to obtain an optimized drug dosage conversion scheme.

8. The precise drug conversion system according to claim 1, characterized in that: Also includes: The data storage and update module is used to communicate with the cloud database to update and store data, as well as to store and back up the received data.

9. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the drug precision conversion system according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a precise drug conversion system as described in any one of claims 1 to 8 is implemented.

Images