Hospital medication management system

Abstract

The invention discloses a hospital medication management system. The hospital medication management system relates to the technical field of medicine management and comprises an information management module; an information processing module; a cloud database module; a medication safety monitoring module; and an adverse reaction module. According to the invention, the collected initial information of the hospital patient is preprocessed to obtain the information of the hospital patient, the information of the hospital patient is converted into the data of the hospital patient, and then the identity of the hospital patient is identified through the stored hospital medication management data of the hospital patient. The method comprises the following steps: acquiring hospital patient data, performing hospital medication compatibility reaction monitoring on hospital patients according to the hospital patient data to obtain a monitoring result, and finally extracting adverse reactions of medicines according to the obtained monitoring result and performing adverse reaction treatment, thereby improving medication safety management efficiency and solving the problem of low medication safety management efficiency in the prior art.

Description

Hospital medication management system Technical Field

[0001] The present invention relates to the technical field of drug management, and in particular to a hospital drug management system. Background Art

[0002] With the surging tide of the big data era, the healthcare sector is also experiencing a surge in the accumulation of massive amounts of data. This process has not only profoundly transformed the industry but also provided unprecedented opportunities for improving the quality of medical services. To achieve excellence in patient care, the key lies in deeply mining and refining each patient's valuable data, meticulously forging highly accurate feature labels. These refined feature labels act like clues for medical detectives, enabling us to understand disease trends and paving the way for personalized treatment plans.

[0003] Existing hospital medication management systems leverage this data-driven insight to power a significant leap forward in overall hospital service quality and management effectiveness. Through intelligent analysis of patient data, hospitals can pinpoint weaknesses in their services and enhance patient satisfaction. At the management level, the in-depth application of big data can help hospitals optimize resource allocation, improve operational efficiency, and ensure that medical resources flow promptly and accurately to where they are most needed. In short, big data technology is leading the healthcare industry's transformation towards a more efficient, personalized, and patient-centric service model, ushering in a new era of smart healthcare.

[0004] For example, the invention patent announcement with announcement number: CN114049970B discloses a medication management method and system based on multi-terminal data sharing, including: setting up medication management terminals in multiple related scenarios for specific drugs, and recording the multimodal data of the corresponding drugs through the medication management terminals in each scenario; obtaining multimodal data from the drug management terminal through encrypted transmission and inputting it into a pre-trained semi-supervised multimodal neural network to obtain the medication preference characteristics of the target object; recording the multimodal data generated during the interaction between the target object and the corresponding drug management terminal through an electronic tag; generating a key through a reader and outputting the key to the electronic tag; inputting the medication preference characteristics into a classifier to obtain the abnormal medication behavior detection results and drug efficacy evaluation results.

[0005] For example, the invention patent announcement with announcement number CN117438023B discloses a big data-based hospital information management method and system, which includes the following steps: obtaining data information of hospital patients; dividing the patient data information into patient attribute information and medical attribute information; performing attention learning on the patient data information in the time dimension through an LSTM recurrent neural network to obtain similarity weights for each preset time step; performing weighted calculation on the similarity weights to obtain each time step vector, and normalizing each time step vector to obtain a user portrait label for the patient; performing data slicing, dicing, and rotation operations based on the user portrait label to obtain a user portrait of each patient; performing medium- and short-term multi-level fusion time series prediction analysis on the patient user portrait using a multi-level encoder according to a single-step prediction method and a multi-step prediction method; obtaining the output sequence of the previous multi-level encoder as a first coding sequence; decomposing the sequence obtained by adding the first coding sequence to the second coding sequence to obtain a time series component; fusing the high-frequency fluctuation component and the low-frequency fluctuation component into the time series component, and performing prediction analysis on the time series component according to the time series decomposition network; and predicting the condition of each patient within a preset time.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the existing technology, traditional hospital medication management systems only have identity recognition and execution of medical order signature functions, which requires nurses to memorize numerous drug combinations when executing medication orders, and personnel may make medication errors, resulting in low efficiency in medication safety management.

[0008] Summary of the Invention

[0009] The embodiments of the present application solve the problem of low efficiency of medication safety management in the prior art by providing a hospital medication management system, thereby improving the efficiency of medication safety management.

[0010] An embodiment of the present application provides a hospital medication management system, comprising: an information management module, an information processing module, a cloud database module, a medication safety monitoring module and an adverse reaction module: wherein the information management module is used to collect initial information of hospital patients, and the initial information includes initial patient basic information, initial medical attribute information and initial patient medication information; the information processing module is used to pre-process the initial hospital patient information of hospital patients to obtain hospital patient information, and convert the hospital patient information into hospital patient data, and the hospital patient data includes patient basic data, medical attribute data and patient medication data; the cloud database module is used to store hospital medication management data of hospital patients, and the hospital medication management data includes hospital patient portrait labels and patient medication data; the medication safety monitoring module is used to monitor hospital medication compatibility reactions of hospital patients based on hospital patient data to obtain monitoring results, and the monitoring results are used to describe the real-time monitoring and judgment of drug use by hospital patients; the adverse reaction module is used to extract adverse reactions of drugs based on the obtained monitoring results and perform adverse reaction processing.

[0011] Furthermore, the specific method for obtaining the conversion evaluation index is as follows: obtaining a conversion micro-evaluation coefficient of the hospital patient information of the hospital patient in the process of form conversion, the conversion micro-evaluation coefficient including information accuracy, information missing rate, information repetition rate and information change rate, the information accuracy represents the proportion of accurate data of the hospital patient information of the hospital patient, the information missing rate represents the proportion of missing information of the hospital patient information of the hospital patient, the information repetition rate represents the proportion of repeated information of the hospital patient information of the hospital patient, and the information change rate represents the number of times the hospital patient information of the hospital patient changes within a unit time; obtaining a conversion micro-evaluation score based on the obtained conversion micro-evaluation coefficient, the conversion micro-evaluation score including information accuracy score, information missing rate score, information repetition rate score and information change rate score; obtaining a conversion evaluation index of the hospital patient based on the obtained conversion micro-evaluation score, the conversion evaluation index is calculated using the following formula:

[0012] Where, e is a natural constant, m represents the number of hospital patients, m = 1, 2, ..., M, M is the total number of hospital patients, mn represents the hospital patient information number of the mth hospital patient, mn = m.1, m.2, ..., mN, mN is the total number of hospital patient information of the mth hospital patient, ZH m is the conversion evaluation index of the mth hospital patient, B' m is the information accuracy score of the mth hospital patient, Q' m is the information missing rate score of patients in the mth hospital, C' m is the information duplication rate score of the patients in the mth hospital, V'm.n is the information change rate score of the mnth operating parameter data of the patient in the mth hospital.

[0013] Furthermore, the specific method for obtaining the identity recognition index is as follows: extracting identity recognition indicators from the basic patient data of hospital patients and performing data normalization, the identity recognition indicators including facial similarity, voice similarity and age change rate, the facial similarity being obtained by performing facial comparison between hospital patients and hospital patient portrait labels, the voice similarity being obtained by performing voice comparison between hospital patients and hospital patient portrait labels, and the age change rate representing the rate of change of face and voice with age obtained according to an age growth model; obtaining an identity recognition indicator coefficient based on the obtained identity recognition indicators, the identity recognition indicator coefficient including a facial similarity coefficient, a voice similarity coefficient and an age change rate coefficient; obtaining the identity recognition index of the hospital patient based on the obtained identity recognition indicator coefficient.

[0014] Furthermore, the specific method for obtaining the inventory demand matching index is as follows: extracting the inventory demand matching index within a preset time interval from the hospital patient data of the hospital patients and normalizing the data, the inventory demand matching index including the drug inventory and drug demand; obtaining the inventory demand matching index of the hospital patients based on the obtained inventory demand matching index.

[0015] Furthermore, the inventory demand matching index is calculated using the following formula:

[0016] Where m represents the number of hospital patients, m = 1, 2, ..., M, M is the total number of hospital patients, j represents the drug category number of hospital patients, j = 1, 2, ..., J, J is the total drug category of hospital patients, PW is the inventory demand matching index, is the drug inventory of the jth drug category for the mth hospital patient, G' j is the drug demand of the jth drug category.

[0017] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0018] 1. Hospital patient information is obtained by pre-processing the collected initial information of hospital patients, and the hospital patient information is converted into hospital patient data. Then, the hospital patient identity is identified through the stored hospital medication management data of the hospital patients. Then, the hospital medication compatibility reaction of the hospital patients is monitored based on the hospital patient data to obtain monitoring results. Finally, the adverse reactions of the drugs are extracted based on the obtained monitoring results and the adverse reactions are processed, thereby realizing the detection of the interaction between different groups of drugs in the hospital, and then realizing the improvement of the efficiency of medication safety management, and effectively solving the problem of low efficiency of medication safety management in the existing technology.

[0019] 2. The conversion micro-assessment coefficient of the hospital patient information obtained during the form conversion process of the hospital patient is used to obtain the conversion micro-assessment score, and then the conversion assessment index of the hospital patient is obtained based on the obtained conversion micro-assessment score. Finally, the efficiency of the form conversion of the hospital patient information is evaluated through the obtained conversion assessment index, thereby realizing the quantification of the form conversion efficiency of the hospital patient information, and further realizing a more accurate evaluation of the form conversion efficiency of the hospital patient information.

[0020] 3. By extracting the inventory demand matching index within a preset time interval from the hospital patient data of the hospital patients, and then obtaining the hospital patient inventory demand matching index based on the obtained inventory demand matching index, and finally evaluating the matching degree between the drug inventory and actual demand through the obtained inventory demand matching index, the matching degree between the drug inventory and actual demand is quantified, thereby achieving a more accurate evaluation of the matching degree between the drug inventory and actual demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a schematic diagram of the structure of a hospital medication management system provided by an embodiment of the present application;

[0022] FIG2 is a schematic diagram of the structure of an information management module in a hospital medication management system according to an embodiment of the present application;

[0023] FIG3 is a schematic diagram of the structure of an information processing module in a hospital medication management system according to an embodiment of the present application;

[0024] FIG4 is a schematic diagram of the structure of a cloud database module in a hospital medication management system provided by an embodiment of the present application;

[0025] FIG5 is a statistical diagram of changes in the identity recognition index provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The embodiment of the present application solves the problem of low efficiency of medication safety management in the prior art by providing a hospital medication management system. It collects initial information of hospital patients, pre-processes the initial hospital patient information of hospital patients to obtain hospital patient information, and converts the hospital patient information into hospital patient data. Then, the hospital patient identity is identified through the stored hospital medication management data of the hospital patients. At the same time, the hospital medication compatibility reaction of the hospital patients is monitored based on the hospital patient data to obtain monitoring results. Finally, the adverse reactions of the drugs are extracted based on the obtained monitoring results and the adverse reactions are processed, thereby achieving improved efficiency in medication safety management.

[0027] The technical solution in the embodiments of the present application is to solve the problem of low efficiency in medication safety management. The overall idea is as follows:

[0028] Hospital patient information is obtained by preprocessing the collected initial information of hospital patients, and the hospital patient information is converted into hospital patient data. The hospital patient identity is then identified through the stored hospital medication management data of the hospital patients. Then, the hospital medication compatibility reaction of the hospital patients is monitored based on the hospital patient data to obtain monitoring results. Finally, the adverse reactions of the drugs are extracted based on the monitoring results and the adverse reactions are handled, thereby improving the efficiency of medication safety management.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0030] As shown in Figure 1, it is a structural diagram of the hospital medication management system provided by the embodiment of the present application. The hospital medication management system provided by the embodiment of the present application includes: an information management module, an information processing module, a cloud database module, a medication safety monitoring module and an adverse reaction module: wherein the information management module is used to collect the initial information of the hospital patients, the initial information includes the initial patient basic information, the initial medical attribute information and the initial patient medication information, the initial patient basic information represents the identity information corresponding to the hospital patients, the initial medical attribute information represents the hospital allocation information corresponding to the hospital patients, and the initial patient medication information represents the medication records corresponding to the hospital patients; the information processing module is used to pre-process the initial hospital patient information of the hospital patients to obtain the hospital patient information. The cloud database module is used to store the hospital medication management data of hospital patients. The hospital medication management data includes hospital patient portrait tags and patient medication data. The hospital patient portrait tags are used to identify the identity of hospital patients. The medication safety monitoring module is used to monitor the hospital medication compatibility reactions of hospital patients based on the hospital patient data to obtain monitoring results. The monitoring results are used to describe the real-time monitoring and judgment of the use of drugs by hospital patients. The adverse reaction module is used to extract the adverse reactions of drugs based on the monitoring results and perform adverse reaction processing. The adverse reaction processing includes reaction feedback and reaction storage.

[0031] In this embodiment, the nurse's mobile terminal can monitor the compatibility reactions between drugs by scanning the drugs used by hospital patients, and report to the preset doctor when an adverse reaction is prompted. The preset doctor can then determine the route of medication or change the drug. This can reduce the potential risks of medication for hospital patients, reduce the nurse's memory of numerous drug compatibility reactions, reduce nursing errors, and protect patients' medication safety; thus achieving improved efficiency in medication safety management.

[0032] Furthermore, as shown in Figure 2, which is a structural diagram of the information management module in the hospital medication management system provided in an embodiment of the present application, the information management module includes a patient basic information unit, a medical attribute information unit and a patient medication information unit; the patient basic information unit: used to generate a patient portrait based on the collected patient basic information of the hospital patients to obtain a hospital patient portrait label corresponding to the hospital patients, and to identify the corresponding hospital patient portrait label; the medical attribute information unit: used to collect the medical attribute information of the hospital patients; the patient medication information unit: used to collect the patient medication information of the hospital patients, and the patient medication information is used to record the drug usage of the hospital patients in a historical time period.

[0033] In this embodiment, the basic patient information includes the patient's gender, age, and disease type; the medical attribute information includes the hospital patient's affiliated hospital, department, and treatment plan; all of which can be added or deleted according to actual conditions; thus, the comprehensiveness of the acquisition of various types of information on hospital patients is improved, further improving the efficiency of medication safety management.

[0034] Furthermore, as shown in Figure 3, which is a structural diagram of the information processing module in the hospital medication management system provided in an embodiment of the present application, the information processing module includes a preprocessing unit, an information data conversion unit and a secondary data processing unit; the preprocessing unit: is used to preprocess the initial hospital patient information to obtain hospital patient information, and the preprocessing includes text preprocessing, information completion and information cleaning; the information data conversion unit: is used to perform form conversion on the acquired hospital patient information using a bag-of-words model and perform conversion evaluation on the result of the form conversion to obtain a conversion evaluation index. If the preset conversion evaluation index is met, it is transmitted to the secondary data processing unit, otherwise the form conversion is performed again until the preset conversion evaluation index is met. The conversion evaluation index is used to measure the efficiency of the form conversion of the hospital patient information; the secondary data processing unit: is used to perform secondary data processing on the initial hospital patient data that meets the preset conversion evaluation index to obtain hospital patient data. The secondary data processing includes removing duplicate values, processing missing values ​​and data classification.

[0035] In this embodiment, text preprocessing is to convert the text into lowercase by removing special characters, punctuation marks, numbers, HTML tags and non-alphabetic characters in the initial hospital patient information, and then cut the continuous text sequence into discrete vocabulary units, then remove the words without actual meaning in the text information, and finally restore the different forms of the words to their original stem forms; information completion is mainly to interpolate and supplement through the average value of the effective value of the information; information cleaning is mainly noise information processing, including binning operation, regression processing and outlier analysis; binning operation includes equal width binning and equal frequency binning; equal width binning divides the value range of the continuous variable into several intervals, the width of each interval is equal, and the bin width is selected according to business needs and data characteristics, and then the boundary value of each bin is calculated, the data is distributed according to the bin boundary value, and each observation is binned. The values ​​are classified into corresponding bins; equal-frequency binning groups the values ​​of continuous variables according to frequency so that the number of data contained in each group is the same. The number of bins is selected according to business needs and data characteristics. The boundary value of each bin is calculated according to the quantile of the data, and the data is distributed according to the bin boundary value, and each observation value is classified into the corresponding bin; binning operation is generally adopted to replace the information with its nearest neighbors to smooth and ordered data values. The specific noise information processing method can be selected according to the actual situation; the bag-of-words model is used to treat the preprocessed information as a set of words, create a vocabulary, and create a vector for each document in the vocabulary, where each dimension of the vector corresponds to a word in the vocabulary. If a corresponding word is contained in a document, the corresponding dimension value is the number of times the word appears in the document, and then the term frequency-inverse document frequency (TF-IDF) weighting is performed to obtain the converted hospital patient data; the processing accuracy of the initial hospital patient information obtained is improved, and the efficiency of medication safety management is further improved.

[0036] Furthermore, the specific process of obtaining the monitoring results is as follows: the hospital patient identity is identified based on the acquired hospital patient data and combined with the hospital patient portrait label to obtain an identity identification index. If the identity identification index is consistent with the corresponding hospital patient portrait label, it is determined that the corresponding hospital patient portrait label belongs to the hospital patient, otherwise re-identification is performed. The identity identification index is used to measure the degree of matching between the hospital patient and the hospital patient portrait label; the real-time use of the hospital patients' drugs after determination is combined with the corresponding historical use of drugs for reaction monitoring to obtain monitoring results, and the real-time use of the hospital patients' drugs is evaluated based on the monitoring results to obtain evaluation results, and at the same time, the real-time use of drugs whose evaluation results do not meet the preset requirements is fed back to the preset doctor.

[0037] In this embodiment, a compatibility reaction refers to a phenomenon in which the properties, efficacy or safety of drugs change due to physical or chemical interactions when two or more drugs are mixed. After a compatibility reaction occurs, feedback is given to the preset doctor, who then determines the route of medication or changes the drug. This improves the real-time monitoring of hospital medication management and further improves the efficiency of medication safety management.

[0038] Furthermore, as shown in Figure 4, which is a structural diagram of the cloud database module in the hospital medication management system provided in an embodiment of the present application, the cloud database module includes a hospital patient portrait label unit, a hospital patient medication data unit and a drug inventory unit; the hospital patient portrait label unit: used to store the obtained hospital patient portrait labels of hospital patients; the hospital patient medication data unit: used to store the historical drug effect data of hospital patients, the historical drug effect data includes the historical types of drugs used, the historical quantities of drugs used and the historical drug use conditions; the drug inventory unit: used to compare the inventory of drugs with the actual demand to obtain the inventory demand matching index and feedback it to the preset personnel, the inventory demand matching index is used to describe the degree of matching between the inventory of drugs and the actual demand.

[0039] In this embodiment, the inventory demand matching index is fed back to the preset personnel, who then judge the relationship between the inventory and demand and take corresponding measures; if the inventory is not greater than the demand, the preset personnel are required to replenish the corresponding drugs according to the inventory demand matching index; the classified storage of hospital patient data is realized, further improving the efficiency of medication safety management.

[0040] Furthermore, the adverse reaction module includes a reaction feedback unit and a reaction storage unit; the reaction feedback unit is used to feedback the abnormal reactions of hospital patients that do not exist in the hospital patient medication data unit to the preset pharmacy department for verification to obtain a verification result. If the verification result meets the preset reference value, it is transmitted to the reaction storage unit, otherwise no storage is required; the reaction storage unit is used to store the abnormal reactions of hospital patients that meet the preset reference value and the corresponding drugs used.

[0041] In this embodiment, the verification result is used to determine whether the abnormal reaction of the hospital patient is to be stored. When the abnormal reaction does not need to be stored, the abnormal reaction only needs to be fed back to the preset doctor for medication confirmation. When the abnormal reaction needs to be stored, the drug that causes the abnormal reaction is transmitted together with the abnormal reaction to the reaction storage unit for storage to facilitate subsequent monitoring of drug compatibility reactions; the efficiency of drug compatibility reaction monitoring is improved, and the efficiency of drug safety management is further improved.

[0042] Furthermore, a specific method for obtaining conversion evaluation indicators is as follows: obtaining a conversion micro-evaluation coefficient of hospital patient information of hospital patients in a process of form conversion, the conversion micro-evaluation coefficient including information accuracy, information missing rate, information repetition rate and information change rate, information accuracy indicating the proportion of accurate data of hospital patient information of hospital patients, information missing rate indicating the proportion of missing information of hospital patient information of hospital patients, information repetition rate indicating the proportion of repeated information of hospital patient information of hospital patients, and information change rate indicating the number of times hospital patient information of hospital patients changes within a unit time; obtaining a conversion micro-evaluation score based on the obtained conversion micro-evaluation coefficient, the conversion micro-evaluation score including information accuracy score, information missing rate score, information repetition rate score and information change rate score;

[0043] The information accuracy score is the absolute value of the ratio of the difference between the information accuracy and the corresponding reference value to the corresponding reference deviation; the information missing rate score is the absolute value of the ratio of the difference between the information missing rate and the corresponding reference value to the corresponding reference deviation; the information repetition rate score is the absolute value of the ratio of the difference between the information repetition rate and the corresponding reference value to the corresponding reference deviation; the information change rate score is the absolute value of the ratio of the difference between the information change rate and the corresponding reference value to the corresponding reference deviation; the conversion evaluation index of hospital patients is obtained based on the obtained conversion micro-evaluation score. In addition to being expressed by the proportion of users who complete a specific behavior to the total number of users visiting the website, the conversion evaluation index can also be calculated more accurately by a formula. The conversion evaluation index is calculated using the following formula:

[0044] Where, e is a natural constant, m represents the number of hospital patients, m = 1, 2, ..., M, M is the total number of hospital patients, mn represents the hospital patient information number of the mth hospital patient, mn = m.1, m.2, ..., mN, mN is the total number of hospital patient information of the mth hospital patient, ZH m is the conversion evaluation index of the mth hospital patient, B' m is the information accuracy score of the mth hospital patient, Q' m is the information missing rate score of patients in the mth hospital, C' m is the information duplication rate score of the patients in the mth hospital, V' m.n is the information change rate score of the mnth operating parameter data of the patient in the mth hospital.

[0045] In this embodiment, let Then the conversion evaluation index can be simplified as: The statistical table of changes in conversion evaluation indicators is shown in Table 1:

[0046] Table 1 Statistics of changes in conversion evaluation indicators

[0047] As can be seen from the above table, the conversion evaluation index cannot be directly obtained from a single data set. It needs to be obtained through a comprehensive analysis of the information accuracy score, information missing rate score, information repetition rate score, and information change rate score. For example, the information accuracy score of the first set of data is greater than the information accuracy score of the third set of data, but the final conversion evaluation index is equal. Because the information missing rate score, information repetition rate score, and information change rate score also have an impact, a comprehensive analysis is required.

[0048] It is important to understand that the expression for the information accuracy score is Among them, B m is the information accuracy of patients in the mth hospital, is the reference information accuracy of the patients in the mth hospital, ΔB is the reference deviation of information accuracy; the expression of information missing rate score is Among them, Q m is the information missing rate of patients in the mth hospital, is the reference information missing rate of patients in the mth hospital, ΔQ is the reference deviation of the information missing rate; the expression of the information duplication rate score is Among them, C m is the information duplication rate of patients in the mth hospital, is the reference information repetition rate of patients in the mth hospital, ΔC is the reference deviation of the information repetition rate; the expression of the information change rate score is Among them, V m.n is the information change rate score of the mn-th hospital patient information of the m-th hospital patient, is the reference information change rate of the mn-th hospital patient information of the m-th hospital patient, and ΔV is the reference deviation of the information change rate; the efficiency of the form conversion of hospital patient information is realized by digitization, and the efficiency of medication safety management is further improved; the reference information accuracy is obtained by analyzing and counting the information accuracy of hospital patients and taking the average value, the reference information missing rate is obtained by analyzing and counting the information missing rate of hospital patients and taking the average value, the reference information repetition rate is obtained by analyzing and counting the information repetition rate of hospital patients and taking the average value, and the reference information change rate is obtained by analyzing and counting the information change rate of hospital patients and taking the average value; the information accuracy reference deviation is obtained by analyzing and counting the information accuracy of hospital patients through the reference deviation calculation formula, the information missing rate reference deviation is obtained by analyzing and counting the information missing rate of hospital patients through the reference deviation calculation formula, the information repetition rate reference deviation is obtained by analyzing and counting the information repetition rate of hospital patients through the reference deviation calculation formula, and the information change rate reference deviation is obtained by analyzing and counting the information change rate of hospital patients through the reference deviation calculation formula.

[0049] Furthermore, a specific method for obtaining the identity recognition index is as follows: extracting identity recognition indicators from the basic patient data of hospital patients and performing data normalization, the identity recognition indicators including facial similarity, voice similarity, and age change rate, the facial similarity being obtained by performing facial comparison between hospital patients and hospital patient portrait labels, the voice similarity being obtained by performing voice comparison between hospital patients and hospital patient portrait labels, and the age change rate representing the rate of change of face and voice with age obtained according to an age growth model; obtaining an identity recognition index coefficient based on the obtained identity recognition indicators, the identity recognition index coefficient including a facial similarity coefficient, a voice similarity coefficient, and an age change rate coefficient;

[0050] The facial similarity coefficient is the absolute value of the ratio of the difference between the facial similarity and the corresponding reference value to the corresponding reference deviation. The voice similarity coefficient is the absolute value of the ratio of the difference between the voice similarity and the corresponding reference value to the corresponding reference deviation. The age change rate coefficient is the absolute value of the ratio of the difference between the age change rate and the corresponding reference value to the corresponding reference deviation. The identity recognition index of hospital patients is obtained based on the obtained identity recognition index coefficient.

[0051] In this embodiment, the identity recognition index can be obtained by automatically detecting and tracking faces by collecting images or video streams containing the user's face and comparing the automatically detected and tracked faces in the images or video streams containing the user's face with the user's real-time face when the user performs identity recognition. Alternatively, a formula can be used for more accurate calculation. The identity recognition index is calculated using the following formula:

[0052] Where, e is a natural constant, m represents the number of patients in the hospital, m=1,2,...,M, M is the total number of patients in the hospital, SF m is the identification index of the patient in the mth hospital, F' m is the facial similarity coefficient of the mth hospital patient, Y' m is the voice similarity coefficient of the mth hospital patient, A' m is the age change rate coefficient of patients in the mth hospital.

[0053] Specifically, it is defined as the identity similarity coefficient The identification index can be simplified as: As shown in FIG5 , a statistical diagram of the changes in the identity recognition index provided in the embodiment of the present application is shown. It can be seen from the figure that the identity similarity coefficient and the age change rate coefficient are both positively correlated with the identity recognition index; when the identity similarity coefficient increases, the greater the identity recognition index, the higher the matching degree between the hospital patient and the hospital patient portrait label; when the age change rate coefficient increases, the greater the identity recognition index, the higher the matching degree between the hospital patient and the hospital patient portrait label; the expression of the facial similarity coefficient is Among them, F m is the facial similarity of the patients in the mth hospital, is the reference facial similarity of the mth hospital patient, ΔF is the reference deviation of facial similarity; the expression of the voice similarity coefficient is Among them, Y m is the voice similarity of the patients in the mth hospital, is the reference speech similarity of the mth hospital patient, ΔY is the reference deviation of speech similarity; the expression of the age change rate coefficient is Among them, A m is the age change rate of patients in the mth hospital, is the reference age change rate of the mth hospital patient, and ΔA is the reference deviation of the age change rate; the matching degree between hospital patients and hospital patient portrait labels is digitized, which further improves the efficiency of medication safety management for different groups of medications in the hospital.

[0054] It should be understood that the reference facial similarity is obtained by analyzing and counting the facial similarities of hospital patients and taking the average value, the reference voice similarity is obtained by analyzing and counting the voice similarities of hospital patients and taking the average value, and the reference age change rate is obtained by analyzing and counting the age change rate of hospital patients and taking the average value; the facial similarity reference deviation is obtained by analyzing and counting the facial similarities of hospital patients through the reference deviation calculation formula, the voice similarity reference deviation is obtained by analyzing and counting the voice similarities of hospital patients through the reference deviation calculation formula, and the age change rate reference deviation is obtained by analyzing and counting the age change rate of hospital patients through the reference deviation calculation formula.

[0055] Furthermore, a specific method for obtaining the inventory demand matching index is as follows: extracting inventory demand matching indicators within a preset time interval from hospital patient data of hospital patients and normalizing the data, the inventory demand matching indicators including drug inventory and drug demand; obtaining the inventory demand matching index of hospital patients based on the obtained inventory demand matching indicators.

[0056] In this embodiment, the data is normalized to the maximum absolute value scaling (Max Absolute Scaling, Max Abs), and the inventory demand matching index is mapped to the interval [-1, 1]; the drug inventory is obtained by the preset personnel counting the drug quantity, and the drug demand is obtained based on the records of the preset doctor and the medication records in the hospital patient medication data unit; the inventory demand matching index of the hospital patients is digitized, and the efficiency of medication safety management of different groups of medications in the hospital is further improved.

[0057] Furthermore, in addition to automatically recording inventory and usage through modern supply chain management software and comparing inventory and usage to generate the inventory demand matching index, the inventory demand matching index can also be calculated more accurately through formulas. The inventory demand matching index is calculated using the following formula:

[0058] Where m represents the number of hospital patients, m = 1, 2, ..., M, M is the total number of hospital patients, j represents the drug category number of hospital patients, j = 1, 2, ..., J, J is the total drug category of hospital patients, PW is the inventory demand matching index, is the drug inventory of the jth drug category for the mth hospital patient, G' j is the drug demand of the jth drug category.

[0059] In this embodiment, the degree of matching between drug inventory and actual demand is digitized, further improving the efficiency of medication safety management for different groups of medications in the hospital.

[0060] To summarize, the embodiment of the present application obtains hospital patient information by pre-processing the collected initial information of hospital patients, and converts the hospital patient information into hospital patient data, and then identifies the hospital patient identity through the stored hospital patient medication management data, and then monitors the hospital medication compatibility reactions of hospital patients based on the hospital patient data to obtain monitoring results, and finally extracts the adverse reactions of the drugs based on the obtained monitoring results and performs adverse reaction processing, thereby realizing the detection of interactions between different groups of drugs in the hospital, and further realizing the improvement of the efficiency of medication safety management, and effectively solving the problem of low efficiency of medication safety management in the existing technology.

[0061] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] The present invention is described with reference to the flowcharts and / or block diagrams of the systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0063] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0065] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0066] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. Hospital medication management system, characterized by: Including information management module, information processing module, cloud database module, medication safety monitoring module and adverse reaction module: Wherein, the information management module is used to collect the initial information of hospital patients, and the initial information includes initial patient basic information, initial medical attribute information and initial patient medication information; The information processing module is used to pre-process the initial hospital patient information of the hospital patient to obtain the hospital patient information, and convert the hospital patient information into hospital patient data, wherein the hospital patient data includes basic patient data, medical attribute data and patient medication data; The cloud database module is used to store hospital medication management data of hospital patients, and the hospital medication management data includes hospital patient portrait labels and patient medication data; The medication safety monitoring module is used to monitor the hospital medication compatibility reaction of hospital patients according to the hospital patient data to obtain monitoring results, and the monitoring results are used to describe the monitoring and judgment of the real-time medication use of hospital patients; The adverse reaction module is used to extract adverse reactions of the drug according to the obtained monitoring results and perform adverse reaction treatment.

2. The hospital medication management system as claimed in claim 1, characterized in that: The information management module includes a patient basic information unit, a medical attribute information unit and a patient medication information unit; The patient basic information unit is used to generate a patient portrait based on the collected basic information of the hospital patients to obtain a hospital patient portrait label corresponding to the hospital patients, and to identify the portrait label of the corresponding hospital patients; The medical attribute information unit is used to collect medical attribute information of hospital patients; The patient medication information unit is used to collect the patient medication information of the hospital patients, and the patient medication information is used to record the medication usage of the hospital patients in a historical time period.

3. The hospital medication management system as claimed in claim 1, characterized in that: The information processing module includes a pre-processing unit, an information data conversion unit and a secondary data processing unit; The preprocessing unit is used to preprocess the initial hospital patient information to obtain the hospital patient information; The information data conversion unit is used to convert the acquired hospital patient information using the bag-of-words model and to perform conversion evaluation on the result of the conversion to obtain a conversion evaluation index. If the preset conversion evaluation index is met, the information is transmitted to the second The secondary data processing unit, otherwise, re-converts the form until a preset conversion evaluation index is satisfied, wherein the conversion evaluation index is used to measure the efficiency of the conversion of the form of hospital patient information; The secondary data processing unit is used to perform secondary data processing on initial hospital patient data that meets preset conversion evaluation indicators to obtain hospital patient data.

4. The hospital medication management system as claimed in claim 1, characterized in that: The specific process of obtaining the monitoring results is as follows: The hospital patient identity is identified based on the acquired hospital patient data and combined with the hospital patient portrait label to obtain an identity identification index. If the identity identification index matches the corresponding hospital patient portrait label, it is determined that the corresponding hospital patient portrait label belongs to the hospital patient. Otherwise, the identification is performed again. The identity identification index is used to measure the matching degree between the hospital patient and the hospital patient portrait label. The real-time drugs used by the hospital patients are monitored for compatibility reactions with the corresponding historical drugs to obtain monitoring results, and the real-time drugs used by the hospital patients are evaluated based on the monitoring results to obtain evaluation results. At the same time, the real-time drugs used whose evaluation results do not meet the preset requirements are fed back to the preset doctors.

5. The hospital medication management system as claimed in claim 1, characterized in that: The cloud database module includes a hospital patient portrait label unit, a hospital patient medication data unit and a drug inventory unit; The hospital patient portrait label unit is used to store the obtained hospital patient portrait labels of the hospital patients; The hospital patient medication data unit is used to store historical medication effect data of hospital patients; The drug inventory unit is used to compare the drug inventory with the actual demand to obtain the inventory demand matching index and feed it back to the preset personnel. The inventory demand matching index is used to describe the matching degree between the drug inventory and the actual demand.

6. The hospital medication management system as claimed in claim 1, characterized in that: The adverse reaction module includes a reaction feedback unit and a reaction storage unit; The reaction feedback unit is used to feed back the abnormal reactions of hospital patients that do not exist in the hospital patient medication data unit to the preset pharmacy department for verification to obtain a verification result. If the verification result meets the preset reference value, it is transmitted to the reaction storage unit, otherwise it does not need to be stored. The verification result is used to determine whether the abnormal reactions of hospital patients are stored; The reaction storage unit is used to store abnormal reactions of hospital patients that meet preset reference values ​​and corresponding used drugs.

7. The hospital medication management system as claimed in claim 3, characterized in that: The specific method for obtaining the conversion evaluation index is as follows: Obtaining a conversion micro-assessment coefficient of hospital patient information of hospital patients in a process of form conversion, wherein the conversion micro-assessment coefficient includes information accuracy, information missing rate, information repetition rate and information change rate, wherein the information accuracy represents the proportion of accurate data of hospital patient information of hospital patients, the information missing rate represents the proportion of missing information of hospital patient information of hospital patients, the information repetition rate represents the proportion of repeated information of hospital patient information of hospital patients, and the information change rate represents the number of times the hospital patient information of hospital patients changes within a unit time; Obtaining a conversion micro-assessment score according to the obtained conversion micro-assessment coefficient, wherein the conversion micro-assessment score includes an information accuracy score, an information missing rate score, an information repetition rate score, and an information change rate score; The conversion evaluation index of the hospital patients is obtained according to the obtained conversion micro-evaluation score, and the conversion evaluation index is calculated using the following formula: Wherein, e is a natural constant, m represents the number of hospital patients, m=1,2,...,M, M is the total number of hospital patients, mn represents the hospital patient information number of the mth hospital patient, mn=m.1,m.2,...,mN, mN is the total number of hospital patient information of the mth hospital patient, ZH m is the conversion evaluation index of the mth hospital patient, B' m is the information accuracy score of the mth hospital patient, Q' m is the information missing rate score of patients in the mth hospital, C' m is the information duplication rate score of the mth hospital patient, V' m.n It is the information change rate score of the mnth operating parameter data of the patient in the mth hospital.

8. The hospital medication management system as claimed in claim 4, characterized in that: The specific method for obtaining the identity recognition index is as follows: The identification index is extracted from the basic patient data of the hospital patients and the data is normalized. The identification index includes facial similarity, voice similarity and age change rate. The facial similarity is calculated by comparing the hospital patients with the hospital patients. The voice similarity is obtained by comparing the voices of hospital patients with hospital patient portrait labels, and the age change rate represents the speed of change of face and voice with age obtained according to the age growth model; Obtaining identity recognition index coefficients according to the obtained identity recognition indexes, wherein the identity recognition index coefficients include a facial similarity coefficient, a voice similarity coefficient, and an age change rate coefficient; The identity recognition index of hospital patients is obtained according to the obtained identity recognition index coefficient.

9. The hospital medication management system as claimed in claim 5, characterized in that: The specific method for obtaining the inventory demand matching index is as follows: Extracting inventory demand matching indicators within a preset time interval from hospital patient data of hospital patients and performing data normalization, the inventory demand matching indicators including drug inventory and drug demand; The inventory demand matching index of hospital patients is obtained according to the obtained inventory demand matching index.

10. The hospital medication management system as claimed in claim 9, characterized in that: The inventory demand matching index is calculated using the following formula: Where m represents the number of hospital patients, m = 1, 2, ..., M, M is the total number of hospital patients, j represents the drug category number of hospital patients, j = 1, 2, ..., J, J is the total drug category of hospital patients, PW is the inventory demand matching index, is the drug inventory of the jth drug category for the mth hospital patient, G' j is the drug demand of the jth drug category.

Images