Hemodialysis internal fistula puncture needle consumable management system and method thereof

Abstract

The invention discloses a hemodialysis internal fistula puncture needle consumable management system and method, and relates to the technical field of hemodialysis consumable management, and the method specifically comprises the following steps: obtaining consumable demand change information of all abnormal departments in real time, and respectively generating demand fluctuation sensitivity coefficients and abnormal fluctuation evaluation indexes of all abnormal departments; and constructing an abnormal fluctuation evaluation model for the generated demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department, generating an abnormal evaluation coefficient of each abnormal department, and evaluating the abnormal degree of the consumable demand change of each abnormal department. And the abnormal departments are divided into high-degree abnormal departments, medium-degree abnormal departments and low-degree abnormal departments according to evaluation results. According to the invention, through real-time monitoring and intelligent analysis of the consumable demand change of the abnormal department, the problem that inventory distortion and demand abnormity cannot be identified in time in a traditional management mode is solved, and the accuracy and efficiency of consumable management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hemodialysis consumables management, and in particular to a hemodialysis internal fistula puncture needle consumables management system and method thereof. Background Art

[0002] Hemodialysis is a life-sustaining treatment method that removes metabolic waste, toxins and excess water from the patient's blood through extracorporeal circulation. It is often used in the daily treatment of patients with chronic renal failure. The process relies on the fistula puncture needle to draw blood out of the body, filter it and return it to the body. As a crucial consumable in this process, the management of the fistula puncture needle is directly related to the safety, efficiency and cost of treatment. The reason for consumable management of fistula puncture needles is that these needles have strict specification requirements, and the matching model needs to be selected according to the specific situation of the patient, while ensuring that they are used in a sterile environment. In addition, due to the high frequency of use of puncture needle consumables and the continuous need for patient treatment, improper management may lead to inventory shortages or waste, affecting the continuity and effectiveness of treatment. Through scientific consumable management, the risk of using expired and non-compliant consumables can be reduced, the supply chain can be stable, and the rapid investigation of problematic consumables can be guaranteed by using a traceability system, thereby effectively improving medical quality, saving costs and enhancing the patient's treatment experience.

[0003] Existing hemodialysis fistula puncture needle consumables management technology usually relies on the consumables management system for standardized and refined whole-process management. First, the puncture needle consumables are numbered and batched through barcode or RFID technology, and the model, batch number, expiration date and storage location of the consumables are entered into the system to realize automatic information collection and storage. Secondly, in the use of consumables, medical staff record the information of each puncture needle used by scanning codes or electronic registration, and associate it with the patient's treatment record to ensure the traceability of the usage data. For inventory management, the system will update the inventory quantity in real time, and automatically mark the consumables that are about to expire based on the first-in-first-out principle, prompting the administrator to deal with them in time. In addition, through the data analysis function, the system can monitor the frequency of use and inventory status of consumables, predict future demand and generate replenishment plans to avoid shortages or excessive reserves. At the same time, when a problem batch of consumables is found, the system can quickly locate the inventory and usage records, notify relevant personnel to stop using them, and take subsequent remedial measures. The overall process is centered on informatization and automation to ensure efficient, safe and standardized consumables management.

[0004] The prior art has the following deficiencies: In daily consumables management, the demand for consumables in different departments usually fluctuates regularly with changes in treatment plans and the number of patients. However, in some cases, such as new employees' lack of proficiency in operation, special events within the department, or failure to synchronize inventory management data in a timely manner, the frequency of consumables collection in individual departments may suddenly increase abnormally. Since these abnormal collection behaviors usually occur within a specific short period of time, and the existing hemodialysis fistula puncture needle consumables management technology only relies on simple historical records and current data for comparative analysis, it lacks real-time monitoring, dynamic identification, and intelligent early warning functions of demand fluctuation trends, and cannot effectively identify abnormal changes in consumables demand in a timely manner. This problem further causes distortion of inventory data, causing consumables to be consumed rapidly in specific departments, which may lead to inventory shortage risks and affect the normal use of other departments. At the same time, it may also lead to waste due to excessive storage of consumables, ultimately weakening the overall reliability and efficiency of hospital consumables management.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a hemodialysis fistula puncture needle consumables management system and method thereof to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for managing consumables of hemodialysis fistula puncture needles, specifically comprising the following steps: In daily consumables management, the changes in consumables demand of each department are detected in real time, and based on historical data, daily fluctuation range and preset statistical standards, it is determined whether the changes in consumables demand of each department conform to the regular fluctuation pattern; When it is detected that the change trend of the consumables demand of some departments does not conform to the regular fluctuation pattern, these departments are automatically marked as abnormal departments; Obtain the consumables demand change information of all abnormal departments in real time, analyze it after acquisition, and generate the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively; An abnormal fluctuation assessment model is constructed for the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, and the abnormal assessment coefficient of each abnormal department is generated. After the generation, the abnormal degree of the change in the consumables demand of each abnormal department is evaluated, and each abnormal department is divided into a highly abnormal department, a moderately abnormal department and a low abnormal department according to the evaluation results; According to the classification results of each abnormal department, corresponding consumables management measures are taken for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; Continuously monitor changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjust evaluation models and management strategies based on real-time data to optimize consumables management efficiency and reliability.

[0008] Preferably, the consumables demand change information of all abnormal departments is obtained in real time, and analyzed after acquisition to generate the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively, which specifically includes the following steps: Obtain the consumables demand change information of all abnormal departments in real time and perform pre-processing after acquisition; Extracting demand volatility measurement information and demand volatility analysis information from the pre-processed consumables demand change information of all abnormal departments; The extracted demand volatility measurement information and demand volatility analysis information are analyzed to generate the demand volatility sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively.

[0009] Preferably, the logic for obtaining the demand fluctuation sensitivity coefficient of each abnormal department is as follows: Extract the demand volatility measurement information from the preprocessed consumable demand change information of all abnormal departments, including the number of consumables used in each abnormal department at different times within a period of time, the number of hemodialysis patients, and the total number of treatments for hemodialysis patients, and mark them as , and , Indicates that within a period of time Moment The number of consumables used in each abnormal department, Indicates that within a period of time Moment The number of hemodialysis patients in the abnormal department, Indicates that within a period of time Moment Total number of treatments for hemodialysis patients by abnormal departments, , , and are all positive integers; The mean of the number of consumables used in each abnormal department at different times during the time period, the mean of the number of hemodialysis patients, and the mean of the total number of treatments for hemodialysis patients are calculated. The specific calculation formula is as follows: In the formula, For different times in this time period The average number of consumables used in the abnormal departments, For different times in this time period The mean number of hemodialysis patients in each abnormal department, For different times in this time period The average number of treatments for hemodialysis patients in the abnormal departments; Calculate the demand fluctuation sensitivity coefficient of each abnormal department. The specific calculation formula is as follows: In the formula, For the The demand fluctuation sensitivity coefficient of each abnormal department.

[0010] Preferably, the logic for obtaining the abnormal fluctuation assessment index of each abnormal department is as follows: Extract the demand volatility analysis information from the preprocessed consumable demand change information of all abnormal departments, including the standard deviation of the consumable usage quantity of each abnormal department in the historical time period, the standard deviation of the number of hemodialysis patients, and the standard deviation of the consumable usage quantity of each abnormal department in the current time period, and mark them as , and , Indicates that in the historical period The standard deviation of the number of consumables used in the abnormal departments, Indicates that in the historical period The number of hemodialysis patients in the abnormal department, Indicates the number of The standard deviation of the number of consumables used in the abnormal departments, , is a positive integer; Calculate the abnormal fluctuation assessment index of each abnormal department. The specific calculation formula is as follows: In the formula, For the The abnormal fluctuation assessment index of each abnormal department.

[0011] Preferably, an abnormal fluctuation assessment model is constructed based on the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department to generate an abnormal assessment coefficient of each abnormal department, which specifically includes the following steps: The demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficients of several abnormal departments generated in the past period of time are collected and calibrated as , and , Indicates the demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficient numbers of several abnormal departments generated in the past period of time. , is a positive integer, and the data collected in the past period of time forms a historical data set; The multivariate regression model is selected as the abnormal fluctuation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: In the formula, , and is the regression coefficient; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of Using the final regression coefficient, the constructed abnormal fluctuation assessment model is input with the demand fluctuation sensitivity coefficient of each abnormal department generated in real time. and abnormal volatility assessment index , generate abnormal assessment coefficients of each abnormal department in real time .

[0012] Preferably, the abnormal evaluation coefficients of each abnormal department generated The pre-set abnormal evaluation coefficient threshold interval Compare and evaluate the abnormal degree of the change in consumables demand of each abnormal department according to the comparison results, and divide each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the evaluation results. The specific comparison analysis and division are as follows: like , the abnormal degree of the change in the consumables demand of the abnormal department is low, and the abnormal department is classified as a low-abnormal department; like , the abnormal degree of the change in the consumables demand of the abnormal department is moderate, and the abnormal department is classified as a moderately abnormal department; like The abnormal degree of the change in the demand for consumables in the abnormal department is high, and the abnormal department is classified as a highly abnormal department.

[0013] Preferably, according to the classification results of each abnormal department, corresponding consumables management measures are respectively taken for the highly abnormal department, the moderately abnormal department and the low abnormal department, specifically: For abnormal departments classified as low-abnormal departments, the consumables management measures taken are: regularly monitor the changes in the consumables demand of the department to ensure the stability of its consumables management, and issue a mild warning to remind management personnel to pay attention to the demand situation of the department; For abnormal departments classified as moderately abnormal departments, the consumables management measures taken are: allocate consumables replenishment plans for the departments, and dynamically adjust the replenishment frequency and quantity based on real-time data to ensure that inventory management is adapted to demand fluctuations, and issue moderate warnings to prompt management personnel to strengthen monitoring and adjust inventory replenishment strategies based on historical data; For abnormal departments classified as highly abnormal departments, the consumables management measures taken are as follows: focus on monitoring the changes in the consumables demand of the department, and immediately issue a high-intensity warning, activate the emergency replenishment mechanism, prompt management personnel to take emergency replenishment measures, and quickly mobilize spare inventory resources, conduct a detailed analysis of the demand fluctuations of the department, and provide improvement plans.

[0014] Preferably, the hemodialysis fistula puncture needle consumables management system includes a consumables demand fluctuation monitoring module, an abnormal department identification and marking module, an abnormal department data analysis module, an abnormal fluctuation assessment modeling module, a dynamic consumables management measures module, and a real-time monitoring and optimization adjustment module; The consumables demand fluctuation monitoring module detects the changes in the consumables demand of each department in real time during daily consumables management, and determines whether the changes in the consumables demand of each department conform to the regular fluctuation pattern based on historical data, daily fluctuation range and preset statistical standards; The abnormal department identification and marking module automatically marks departments as abnormal departments when it detects that the change trend of the consumables demand of departments does not conform to the regular fluctuation pattern; The abnormal department data analysis module obtains the consumables demand change information of all abnormal departments in real time, analyzes it after acquisition, and generates the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively; The abnormal fluctuation assessment modeling module builds an abnormal fluctuation assessment model for the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, generates the abnormal assessment coefficient of each abnormal department, and analyzes it after generation to assess the abnormal degree of the change in the consumables demand of each abnormal department, and divides each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the assessment results; Dynamic consumables management measures module, based on the classification results of each abnormal department, takes corresponding consumables management measures for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; The real-time monitoring and optimization adjustment module continuously monitors the changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjusts the evaluation model and management strategy based on real-time data to optimize the efficiency and reliability of consumables management.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention detects the changes in the demand for consumables of each department in real time, and combines historical data, fluctuation range and statistical standards to determine whether it conforms to the regular fluctuation pattern, thereby realizing intelligent identification and monitoring of fluctuations in consumables demand. The technical effect of this solution is that it can dynamically detect abnormal fluctuations in the demand for consumables of each department, especially for sudden fluctuations in demand caused by unskilled operation, new employees joining or internal events, and can quickly identify and mark them. The automated identification and early warning functions of this process significantly improve management efficiency, reduce the workload of manual monitoring, and avoid the risk of inventory data distortion, ensuring that the consumables demand of each department can be accurately predicted and responded to in a timely manner.

[0016] 2. The present invention conducts an in-depth analysis of the demand changes in abnormal departments by establishing a model of demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index. This analysis can not only clarify the specific degree of abnormal fluctuations, but also carry out refined hierarchical management of each department, further improving the accuracy and scientificity of consumables management. The distinction between highly abnormal departments, moderately abnormal departments and low abnormal departments allows different management measures to be taken according to different degrees of abnormality, such as mild warnings, dynamic replenishment and emergency replenishment. This hierarchical and dynamically adjusted management method makes consumables management more flexible and efficient, and can take the most appropriate measures according to specific circumstances, ensure the rational allocation of resources, and avoid the risk of inventory backlogs or shortages.

[0017] 3. Another significant advantage of the present invention is that the system design based on dynamic real-time monitoring and optimization adjustment can continuously optimize the consumables management strategy. The real-time monitoring module dynamically adjusts the evaluation model and management strategy according to the actual demand changes and the execution effect of the management measures to ensure that the strategy is always consistent with the fluctuations in departmental demand. This mechanism can optimize the consumables management strategy at different times and under different circumstances, further improve the reliability and flexibility of management, effectively reduce the problem of excess or insufficient inventory caused by the traditional management model, and maximize the overall effectiveness and efficiency of hospital consumables management. Therefore, the technical solution of the present invention is significantly innovative and can provide continuous optimization and intelligent consumables management support under a dynamically changing demand environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 The present invention is a flowchart of the hemodialysis fistula puncture needle consumables management system and method thereof.

[0020] Figure 2 The module diagram of the hemodialysis fistula puncture needle consumables management system and method of the present invention is shown. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0022] The present invention provides Figure 1 The hemodialysis fistula puncture needle consumables management method shown specifically includes the following steps: In daily consumables management, the changes in consumables demand of each department are detected in real time, and based on historical data, daily fluctuation range and preset statistical standards, it is determined whether the changes in consumables demand of each department conform to the regular fluctuation pattern; In daily consumables management, real-time detection of changes in consumables demand in each department can be achieved by integrating the hospital's internal information management system and the Internet of Things technology. Specifically, during the use of consumables, the use of consumables in each department can be tracked in real time through RFID tags, barcode scanners, and intelligent inventory management systems. Each time a consumable is used, the system will record detailed information such as the quantity, time, department, and operator of the consumable. These data are uploaded to the central database in real time via a wireless network to ensure that the management system can reflect changes in consumables demand in each department at every moment. In this way, the dynamics of consumables use in departments at different time points can be captured in real time, ensuring that the management system can obtain data updates in a timely manner and reflect the consumption of consumables in real time.

[0023] Based on historical data, daily fluctuation range and preset statistical standards, judging whether the changes in the demand for consumables in each department conform to the regular fluctuation pattern first requires relying on the hospital's historical records of consumables use, which provide a basis for analyzing the normal fluctuations in departmental demand. Through retrospective analysis of historical data, the trend and fluctuation pattern of consumables use in each department in different time periods can be extracted, and then the normal fluctuation range of the department can be calculated. The daily fluctuation range is calculated based on factors such as the frequency of use and the amount of use of each department in the historical data. These data reflect the fluctuation limit of departmental demand under normal circumstances. The preset statistical standards involve further quantitative analysis of historical data, such as calculating statistical quantities such as the mean, standard deviation, and coefficient of fluctuation of the data, and combining methods such as Z-Score or control charts to determine whether the current data exceeds the normal fluctuation range, thereby identifying potential abnormal situations. In this way, the system can automatically determine whether the changes in consumables demand conform to the regular fluctuation pattern, promptly discover any possible abnormal fluctuations, and avoid problems caused by data lag or human analysis errors in traditional methods.

[0024] This real-time monitoring and data-driven analysis method can solve the common technical bottlenecks in the current traditional consumables management. Most existing technologies rely on static historical data comparison and analysis, which is difficult to handle frequent changes and sudden demand fluctuations, resulting in distorted inventory management, shortages or waste of consumables, and even affecting the normal use of other departments in the hospital. By introducing real-time monitoring and intelligent analysis, not only can potential problems be discovered at the early stage of data changes, but also changes can be responded to in real time by dynamically updating and adjusting the model, avoiding the lag of inventory management. Such a system can analyze the normal fluctuation range of departmental consumables demand through algorithms, detect abnormal fluctuations in time and automatically mark abnormal departments, providing an accurate basis for subsequent management measures. Through this intelligent real-time monitoring and evaluation method, hospitals can optimize resource allocation while reducing manual intervention, improve the efficiency and accuracy of consumables management, and ensure the stability of hospital operations and the optimal allocation of resources.

[0025] When it is detected that the change trend of the consumables demand of some departments does not conform to the regular fluctuation pattern, these departments are automatically marked as abnormal departments; To achieve the function of "automatically marking departments as abnormal departments when the change trend of consumables demand in departments does not conform to the regular fluctuation pattern", we first need to rely on the combination of data analysis and intelligent algorithms. Specifically, this can be achieved by setting thresholds, dynamic monitoring and anomaly detection models. The system will evaluate the current demand changes of each department in real time through algorithms based on the historical consumables demand data of each department and the preset fluctuation range. If the change in consumables demand of a department exceeds the normal fluctuation range, or deviates from the set statistical standards (such as mean ± standard deviation, or outliers calculated using methods such as Z-Score), the system will automatically determine it as an abnormal fluctuation. At the same time, the anomaly detection algorithms in machine learning (such as isolation forest, DBSCAN clustering algorithm, etc.) can be combined to further improve the detection accuracy. Through these intelligent algorithms, the system can not only identify sudden fluctuations in consumables demand, but also predict and automatically adjust according to the patterns trained by historical data, and accurately identify those demand fluctuations caused by improper operation, inventory errors or other abnormal reasons. Departments marked as abnormal will automatically generate alarms, and managers can perform subsequent processing based on the alarm information. This process completely relies on the system's data input and algorithm judgment, and can achieve efficient and real-time anomaly detection.

[0026] Obtain the consumables demand change information of all abnormal departments in real time, analyze it after acquisition, and generate the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively; In this embodiment, the consumables demand change information of all abnormal departments is obtained in real time, and analyzed after acquisition to generate the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively, which specifically includes the following steps: Obtain the consumables demand change information of all abnormal departments in real time and perform pre-processing after acquisition; Real-time acquisition of consumable demand change information for all abnormal departments can be achieved in the following ways: First, the hospital's consumable management system and department resource management system can be used to connect data with the existing electronic medical record system, inventory management system, and patient information management system through the API interface. In this way, the system can automatically obtain the consumable usage data of each department in real-time operation, including the daily consumable consumption of each department, the treatment data of patients in the department (such as treatment plan, number of patients, etc.), and the corresponding inventory consumption information. In addition, the system can monitor the use of consumables in real time through sensors and IoT devices (such as smart cards, RFID tags, etc.) to further strengthen the detection of abnormal situations. Based on the real-time data stream, the system will track and record the changes in consumable demand for each department through the data acquisition module, especially focusing on monitoring and marking those departments that may have abnormal demand fluctuations, so as to achieve accurate dynamic management and monitoring.

[0027] The purpose of preprocessing is to ensure the availability, accuracy and consistency of the acquired data, because the raw data often contains noise, missing values ​​and outliers. If these problems are not handled, they may affect the subsequent analysis results. The steps of preprocessing include: first, fill or delete missing values ​​in the data to ensure that each record is complete. Secondly, use anomaly detection algorithms (such as Z-score-based outlier detection or IQR-based detection methods) to eliminate obviously wrong or extreme values, such as unreasonable consumables consumption data. Then, perform data standardization or normalization to convert indicators of different dimensions (such as consumables demand, number of patients, etc.) into a unified scale to avoid the deviation between data of different magnitudes affecting the analysis results. Finally, it is necessary to smooth the time series data to eliminate the impact of short-term fluctuations, ensure that the data presents a stable fluctuation in the long-term trend, and avoid short-term noise from misleading the subsequent demand fluctuation assessment. After preprocessing, the data will be more accurate and reliable, which is convenient for the subsequent generation of accurate fluctuation sensitivity and anomaly assessment index.

[0028] Extracting demand volatility measurement information and demand volatility analysis information from the pre-processed consumables demand change information of all abnormal departments; The extracted demand volatility measurement information and demand volatility analysis information are analyzed to generate the demand volatility sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively.

[0029] In this embodiment, the logic for obtaining the demand fluctuation sensitivity coefficient of each abnormal department is as follows: Extract the demand volatility measurement information from the preprocessed consumable demand change information of all abnormal departments, including the number of consumables used in each abnormal department at different times within a period of time, the number of hemodialysis patients, and the total number of treatments for hemodialysis patients, and mark them as , and , Indicates that within a period of time Moment The number of consumables used in each abnormal department, Indicates that within a period of time Moment The number of hemodialysis patients in the abnormal department, Indicates that within a period of time Moment Total number of treatments for hemodialysis patients by abnormal departments, , , and are all positive integers; To extract the demand volatility measurement information from the preprocessed consumable demand change information of all abnormal departments, it can be achieved by designing a data collection and preprocessing system. First, the system needs to obtain the real-time consumable usage data, patient information, and treatment records of each department from the hospital management system or electronic health record (EHR) system. For each abnormal department, the system will mark the department whose consumable demand fluctuations are obviously inconsistent with the regular fluctuation pattern based on the set threshold. Then, the system will collect relevant data of these departments at specific time points according to the preset time interval (such as every hour or every day), including the number of consumables used, the number of hemodialysis patients, and the number of treatments. All of these data are cleaned and preprocessed to remove outliers and missing values ​​to ensure the accuracy and completeness of the extracted data. Through automated data collection tools, the system can extract these data from the hospital database in real time for further use in subsequent volatility analysis.

[0030] When obtaining these quantitative data, the number of consumables used, the number of hemodialysis patients, and the total number of treatments can usually be extracted from the hospital's electronic record system. Specifically, the number of consumables used is usually recorded in the hospital's consumables management system, which records the number of consumables such as dialysis puncture needles consumed by each department at each time point. The number of hemodialysis patients can be obtained by querying the patient's admission, treatment, and discharge records, especially the patient data of the dialysis department. The system will accurately record the number of patients undergoing hemodialysis in the department at each time point. The total number of treatments can be extracted through the operation records of dialysis treatment, recording the number of dialysis treatments each patient received. All of these data can be connected to the hospital management system (such as HIS, LIS system) or a dedicated dialysis management system through an automated data interface, and acquired and stored in the database in real time to provide the required quantitative data for subsequent analysis. During the extraction process, the system also needs to synchronize the time point data to ensure the time consistency of data from different sources.

[0031] The mean of the number of consumables used in each abnormal department at different times during the time period, the mean of the number of hemodialysis patients, and the mean of the total number of treatments for hemodialysis patients are calculated. The specific calculation formula is as follows: In the formula, For different times in this time period The average number of consumables used in the abnormal departments, For different times in this time period The mean number of hemodialysis patients in each abnormal department, For different times in this time period The average number of treatments for hemodialysis patients in the abnormal departments; Calculate the demand fluctuation sensitivity coefficient of each abnormal department. The specific calculation formula is as follows: In the formula, For the The demand fluctuation sensitivity coefficient of each abnormal department.

[0032] When calculating the demand fluctuation sensitivity coefficient, the absolute value is used to measure the fluctuation range of consumables usage, number of patients and number of treatments in order to accurately reflect the impact of fluctuations in various indicators on overall demand changes without being disturbed by the direction of fluctuations (increase or decrease). First, we calculate the difference between the data at each time point ttt and its mean. , and They represent the difference between the amount of consumables used, the number of patients, and the number of treatments and their mean. By taking the absolute value of these differences, we can ignore the sign of the difference and focus only on the magnitude of the fluctuation. Then, we multiply these three fluctuations together. , we can get a comprehensive volatility impact factor, which reflects the combined impact of the combined changes of various factors on the fluctuation of consumables demand. This approach is particularly suitable when multiple factors work together, and can accurately measure their contribution to the overall demand fluctuation. Then, we sum this volatility factor at all time points to get the total volatility impact. The calculation of the denominator evaluates the combined fluctuation of the number of patients and the number of treatments, with the aim of measuring their independent impact on demand fluctuations without considering the amount of consumables used. Through such calculations, the demand fluctuation sensitivity coefficient is finally obtained. It is possible to quantify the degree of fluctuation in consumables demand in abnormal departments while avoiding the offset of the results by negative and positive changes, so that each type of fluctuation can fairly reflect its impact on the total demand fluctuation.

[0033] No. The demand fluctuation sensitivity coefficient of abnormal departments It reflects the degree to which the fluctuations in the demand for consumables, the number of patients, and the number of treatments in the department affect the fluctuations in the overall demand for consumables within a specific period of time. The size of is directly related to the abnormal degree of changes in the consumables demand of the department. When the value of the demand fluctuation sensitivity coefficient is large, it means that the changes in the consumables demand of the department are greatly affected by factors such as the number of patients and the number of treatments, and the fluctuation range of these factors is large, indicating that there are more significant abnormalities in the demand fluctuations of the department. This usually indicates that the department has experienced abnormal demand fluctuations in a certain period of time, which may be caused by a surge in the number of patients, changes in treatment plans, or other management factors. And when When the value is small, it means that the demand for consumables in the department is relatively stable, with small fluctuations, and the changes in the number of patients and the number of treatments have little impact on the demand, indicating that the demand changes in the department conform to the regular fluctuation pattern and the degree of abnormality is low. Therefore, the size of the demand fluctuation sensitivity coefficient can be used as an important indicator to evaluate the degree of abnormality of the change in the demand for consumables in the department. The larger the coefficient value, the higher the degree of abnormality of the demand fluctuation, and vice versa.

[0034] In this embodiment, the logic for obtaining the abnormal fluctuation assessment index of each abnormal department is as follows: Extract the demand volatility analysis information from the preprocessed consumable demand change information of all abnormal departments, including the standard deviation of the consumable usage quantity of each abnormal department in the historical time period, the standard deviation of the number of hemodialysis patients, and the standard deviation of the consumable usage quantity of each abnormal department in the current time period, and mark them as , and , Indicates that in the historical period The standard deviation of the number of consumables used in the abnormal departments, Indicates that in the historical period The number of hemodialysis patients in the abnormal department, Indicates the number of The standard deviation of the number of consumables used in the abnormal departments, , is a positive integer; Extracting the consumable demand change information of all abnormal departments can be achieved in the following ways. First, the system needs to establish a data collection mechanism to automatically obtain the consumable usage data and patient information of each department from the hospital management system or electronic medical record system. These data can be synchronized to the data storage platform (such as a database) regularly through the interface. For the data of abnormal departments, based on the real-time monitoring and dynamic identification system (for example, based on the algorithm to determine whether the consumable demand deviates from the regular fluctuation), the system will mark the departments whose demand fluctuations do not meet expectations. Then, the system extracts information such as the number of consumables used and the number of patients in various historical and current time periods from the departments marked as abnormal. This information can be extracted through SQL query statements or data processing tools, and its standard deviation and other statistical data can be calculated as input data for analysis.

[0035] The acquisition of these three types of quantitative data can be achieved in the following ways. First, the standard deviation of the number of consumables used in each abnormal department within the historical time period can be extracted from the historical data records, and the standard deviation is calculated by counting the number of consumables used in the department within a certain time range (such as the past 1 month or 3 months). Similarly, the standard deviation of the number of hemodialysis patients can be calculated by analyzing the fluctuation of the number of patients in the historical patient data, that is, calculating its standard deviation based on the past patient number data (such as the past 6 months). Finally, the standard deviation of the number of consumables used in each abnormal department within the current time period is obtained by obtaining the consumables usage data of the current department through the real-time monitoring system, and calculating the standard deviation of the number of consumables used in the department in the specified time period (such as the current month or week). These data are extracted through automated scripts or data analysis tools, and real-time or periodic calculations are performed to provide a reliable basis for analysis.

[0036] Calculate the abnormal fluctuation assessment index of each abnormal department. The specific calculation formula is as follows: In the formula, For the The abnormal fluctuation assessment index of each abnormal department.

[0037] When calculating the abnormal fluctuation assessment index of each abnormal department, three types of quantitative data are used: current consumables demand data, historical patient number data, and standard deviation of historical consumables demand data. The core purpose of this calculation method is to accurately assess the abnormal degree of demand changes by analyzing the fluctuation of consumables demand in the department, so as to help the system identify those departments with abnormal fluctuations and take management measures in time. First, the numerator: The numerator contains the standard deviation of the current consumables demand data and the square of the standard deviation of the historical patient number data. The standard deviation of the current consumables demand data reflects the fluctuation range of the consumables demand per unit time in the department. A larger standard deviation indicates a larger demand fluctuation. The standard deviation of the historical patient number data is used to indicate the fluctuation of the number of patients in the department over the past period of time. The fluctuation of the number of patients may affect the consumables demand. Therefore, combining it with the fluctuation of the current consumables demand can more comprehensively assess the abnormality of demand changes. The product of the two (squared in the formula) reflects the combined impact of these two factors. Next, the denominator: The denominator contains two items, namely the square of the standard deviation of the historical consumables demand data and the square of the sum of the standard deviation of the current consumables demand data and the standard deviation of the historical number of patients. The standard deviation of the historical consumables demand data represents the normal fluctuation range of the consumables demand over the past period of time. A larger standard deviation means that the department's consumables demand has changed significantly. The sum of the standard deviation of the current consumables demand data and the standard deviation of the historical number of patients data reflects the joint impact of the two on the current changes in consumables demand. The square of the sum can enhance the weight of the combined impact of these two factors, reflecting the impact of this joint fluctuation on abnormal fluctuations.

[0038] No. Abnormal fluctuation assessment index of abnormal departments The size of is directly related to the degree of abnormality of the change in the consumables demand of the department. Specifically, the larger the evaluation index value, the less consistent the change in the consumables demand of the department is with the regular fluctuation pattern, that is, the fluctuation in demand exceeds the expected normal range, and there may be more serious abnormalities. At this time, the fluctuation in the demand for consumables may be caused by temporary events, improper operation, data synchronization lag and other factors, resulting in a sudden increase or decrease in demand in the short term. On the contrary, if the evaluation index is small, it means that the demand fluctuation of the department is relatively stable, consistent with the normal fluctuation range, the changes are relatively smooth, and the degree of abnormality is low. Therefore, the evaluation index provides hospital managers with a quantitative indicator to help them quickly identify which departments have abnormal fluctuations in the use of consumables, so as to take targeted management measures in a timely manner to prevent problems such as inventory imbalance or waste of resources.

[0039] An abnormal fluctuation assessment model is constructed for the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, and the abnormal assessment coefficient of each abnormal department is generated. After the generation, the abnormal degree of the change in the consumables demand of each abnormal department is evaluated, and each abnormal department is divided into a highly abnormal department, a moderately abnormal department and a low abnormal department according to the evaluation results; In this embodiment, an abnormal fluctuation assessment model is constructed based on the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department to generate an abnormal assessment coefficient of each abnormal department, which specifically includes the following steps: The demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficients of several abnormal departments generated in the past period of time are collected and calibrated as , and , Indicates the demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficient numbers of several abnormal departments generated in the past period of time. , is a positive integer, and the data collected in the past period of time forms a historical data set; In order to collect the demand fluctuation sensitivity coefficient, abnormal fluctuation assessment index and corresponding abnormal assessment coefficient of each abnormal department generated in the past period of time, it is necessary to first perform automated data collection through the hospital's consumables management system, patient management system and historical data repository. Specifically, the system can extract the real-time consumables demand data of each department from the consumables usage records of the department, calculate the fluctuation sensitivity coefficient, and analyze the fluctuation of consumables usage based on statistical methods such as standard deviation or relative volatility. At the same time, the patient management system extracts data such as the number of patients and hospitalization conditions, and calculates the abnormal fluctuation assessment index in combination with the consumables demand data to evaluate whether the demand fluctuation is abnormal. Finally, the system automatically calculates and generates the abnormal assessment coefficient using a regression model based on the historical data set (including the fluctuation sensitivity coefficient and the abnormal fluctuation assessment index). All these data are integrated and automatically updated through the interface between the hospital management system and each subsystem to ensure the timeliness and accuracy of the data without manual intervention, thereby realizing the automatic collection and processing of data.

[0040] Will The value is limited to a positive integer greater than or equal to 3. The purpose is to ensure accurate and stable results when calculating the regression coefficient. The regression model requires enough data points to construct a system of equations to accurately calculate each regression coefficient. In a multiple regression model, the number of regression coefficients determines the number of equations required. Because we need to calculate three regression coefficients, at least three equations are required to ensure the solvability and accuracy of the model. If If it is less than 3, then it is impossible to form a sufficient system of equations and obtain the correct regression coefficient. When it is greater than or equal to 3, it can ensure that each regression coefficient has a corresponding equation for calculation, thus ensuring the validity and reliability of the regression analysis results. In addition, A value greater than or equal to 3 means that the system collects at least three or more historical data sets, so that the regression analysis can be trained based on sufficient historical samples to better fit the actual demand fluctuation pattern and avoid inaccuracy or overfitting due to too small a sample size.

[0041] The multivariate regression model is selected as the abnormal fluctuation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: In the formula, , and is the regression coefficient; The multiple regression model is a statistical analysis method used to analyze the relationship between multiple independent variables (characteristic variables) and a dependent variable (response variable). In this model, a mathematical equation is established by finding the linear relationship between the independent variables and the dependent variables, and the regression coefficient is used to represent the degree of influence of each independent variable on the dependent variable. The multiple regression model is widely used in prediction and pattern recognition in real applications, especially for processing multidimensional data. The reason for choosing the multiple regression model as the abnormal fluctuation assessment model is that it can comprehensively consider the impact of multiple factors on the fluctuation of consumables demand, and can more accurately identify how different factors affect the change of consumables demand in the department. Through training with historical data sets, the value of the regression coefficient can be optimized according to the actual demand fluctuation data, thereby constructing an assessment model with predictive ability. In this model, the regression coefficients represent the degree of influence of the demand fluctuation sensitivity coefficient, the abnormal fluctuation assessment index and other related factors on the change of consumables demand. Reflects the relationship between the demand fluctuation sensitivity coefficient and the actual demand fluctuation, It indicates the relationship between the abnormal fluctuation assessment index and the abnormal demand for consumables. is the intercept of the model, which indicates the basic value of the abnormal assessment coefficient when the demand fluctuation sensitivity coefficient and the abnormal fluctuation assessment index are both zero. The regression coefficient obtained through training can more accurately assess the abnormal demand fluctuation of each department and take corresponding management measures.

[0042] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of Optimizing the regression coefficient by minimizing the error between the predicted value and the actual value is the core step in the multivariate regression model, and the purpose is to ensure that the prediction results of the model are as consistent as possible with the actual data. In regression analysis, we hope that the constructed model can accurately predict the changes in the consumables demand of abnormal departments, and the regression coefficient determines the degree of influence of each independent variable in the model (such as the demand fluctuation sensitivity coefficient and the abnormal fluctuation assessment index, etc.) on the dependent variable (abnormal assessment coefficient). In order to optimize these regression coefficients, the least squares method is usually used. Its basic idea is to calculate the error between the model prediction value and the actual observation value (usually the sum of the squares of the error) and minimize this error. This process iteratively adjusts the value of the regression coefficient, gradually reduces the error, and finally obtains the best regression coefficient. Specifically, minimizing this error can be achieved by numerical calculation methods, such as the gradient descent method, to find the most suitable regression coefficient, thereby ensuring the accuracy and reliability of the model. This process is achieved through the feedback of historical data, so the model can eventually predict the abnormal assessment coefficient of each department according to the actual situation, and further evaluate the abnormal degree of changes in consumables demand.

[0043] Using the final regression coefficient, the constructed abnormal fluctuation assessment model is input with the demand fluctuation sensitivity coefficient of each abnormal department generated in real time. and abnormal volatility assessment index , generate abnormal assessment coefficients of each abnormal department in real time .

[0044] In this embodiment, the abnormal evaluation coefficients of each abnormal department generated are The pre-set abnormal evaluation coefficient threshold interval Compare and evaluate the abnormal degree of the change in consumables demand of each abnormal department according to the comparison results, and divide each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the evaluation results. The specific comparison analysis and division are as follows: like , the abnormal degree of the change in the consumables demand of the abnormal department is low, and the abnormal department is classified as a low-abnormal department; This situation indicates that the changes in the demand for consumables in this department are relatively stable, with small fluctuations. This shows that the use of consumables in the department is basically in line with expectations, and there are no obvious abnormal changes in demand. This classification means that the department does not need too much intervention or resource adjustment in daily management, and the system can classify it as within the normal fluctuation range. For managers, this means that they can give priority to other departments with larger abnormal fluctuations, reducing resource waste and management costs. Therefore, in actual applications, low-abnormal departments do not need too much intervention, saving processing resources and time, and allowing the management system to allocate monitoring resources more efficiently and concentrate on dealing with truly abnormal departments.

[0045] like , the abnormal degree of the change in the consumables demand of the abnormal department is moderate, and the abnormal department is classified as a moderately abnormal department; This situation shows that there are certain fluctuations in the change of consumables demand in this department, but the fluctuation range is still within an acceptable range. At this time, the change in the consumables demand of the department may be caused by some external or accidental factors, such as temporary fluctuations in patient flow or the implementation of a specific treatment plan. The abnormal fluctuations in this case will not have a serious impact on the operation of the entire department, but management still needs to pay attention and make appropriate adjustments. For the system, a department marked as moderately abnormal means that further monitoring and tracking are required to ensure that the demand fluctuations of the department do not exceed the normal fluctuation range. If moderate abnormal fluctuations are not effectively controlled, it may lead to improper allocation of resources and affect the work efficiency of the department. Through this moderate abnormal classification, managers can be provided with certain early warnings to prevent the problem from further deteriorating.

[0046] like The abnormal degree of the change in the demand for consumables in the abnormal department is high, and the abnormal department is classified as a highly abnormal department.

[0047] This situation indicates that the change in the demand for consumables in this department exceeds the normal fluctuation range, and there may be serious abnormalities. The demand fluctuations in this type of department may be caused by internal management problems, abnormal growth in the number of patients, special treatment needs, etc. In this case, the abnormal fluctuations have reached a critical point, indicating that the demand for consumables in this department has changed irregularly, and immediate in-depth investigation and intervention are required. The identification of highly abnormal departments means that there is a greater risk in the operating status of the department, which may affect the resource allocation, material consumption and overall service quality of the department. For managers, timely identification of highly abnormal departments and intervention and adjustment will help avoid further waste of resources and management errors, and ensure the stability of the overall operational efficiency of the hospital. Therefore, marking these departments as highly abnormal will help to control risks in advance, optimize resource allocation, and improve the accuracy and efficiency of department management.

[0048] Determine the "pre-set abnormal assessment coefficient threshold interval "It can be achieved through the analysis of historical data and statistical methods. First, by collecting the abnormal evaluation coefficient data of each department within a certain time range, the data is used to calculate its mean and standard deviation. Specifically, the abnormal evaluation coefficient in the historical data can be analyzed, and the threshold interval can be set by the standard deviation method. In general, the threshold interval can be set to the mean plus or minus a certain multiple of the standard deviation, such as the mean ± 2 times the standard deviation, which can cover most normal fluctuation ranges. If higher accuracy is required or adjustment is required according to actual conditions, the threshold interval can be dynamically adjusted through machine learning models (such as cluster analysis) to enable it to adapt to changes in the needs of different departments. In addition, these thresholds can be manually corrected through expert experience or domain knowledge to ensure the rationality and applicability of the threshold interval. In this way, the threshold interval can be optimized according to the fluctuation characteristics of historical data and actual needs to ensure its effectiveness, and it has good flexibility and adaptability in practical applications.

[0049] According to the classification results of each abnormal department, corresponding consumables management measures are taken for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; In this embodiment, according to the classification results of each abnormal department, corresponding consumables management measures are respectively taken for the highly abnormal department, the moderately abnormal department and the low abnormal department, specifically: For abnormal departments classified as low-abnormal departments, the consumables management measures taken are: regularly monitor the changes in the consumables demand of the department to ensure the stability of its consumables management, and issue a mild warning to remind management personnel to pay attention to the demand situation of the department;

[0050] For abnormal departments that are classified as low-abnormal departments, the consumable management measures taken are to regularly monitor the changes in the consumable demand of the department and ensure the stability of its consumable management, while issuing a mild warning to remind managers to pay attention to the demand of the department. An intelligent monitoring system can be established to collect the consumable demand data of each department in real time, and the data acquisition and analysis module can be used to automatically monitor the changes in department demand. When the system detects that the fluctuation range and frequency of demand are lower than the set threshold, a mild warning is triggered and pushed to the manager via email, SMS or system notification. Regular data collection cycles (such as daily or weekly) can ensure that even in low-abnormal situations, managers can adjust their focus in time to avoid potential inventory problems. Through regular monitoring and mild warnings, managers can pay attention to changes in demand in a timely manner to avoid further aggravation of the problem while ensuring the stability of inventory management.

[0051] For abnormal departments classified as moderately abnormal departments, the consumables management measures taken are: allocate consumables replenishment plans for the departments, and dynamically adjust the replenishment frequency and quantity based on real-time data to ensure that inventory management is adapted to demand fluctuations, and issue moderate warnings to prompt management personnel to strengthen monitoring and adjust inventory replenishment strategies based on historical data; For abnormal departments classified as moderately abnormal departments, the consumables management measures taken are to allocate consumables replenishment plans for the departments, and dynamically adjust the replenishment frequency and quantity based on real-time data to ensure that inventory management is adapted to demand fluctuations. At the same time, moderate warnings are issued to prompt managers to strengthen monitoring and adjust inventory replenishment strategies based on historical data. Through the intelligent inventory management system, real-time data (such as daily demand and historical data of the department) can be used to generate dynamic replenishment plans. The system can automatically calculate and adjust the replenishment frequency and quantity based on the current inventory, consumption rate and demand fluctuations. Moderate warnings are triggered when demand fluctuations reach a certain threshold, reminding managers to increase monitoring and adjust inventory strategies. The system will provide real-time data and replenishment suggestions to ensure that inventory can match actual demand and avoid overstocking or shortages. At the same time, based on the feedback of historical data, the inventory replenishment strategy is continuously optimized to improve the overall inventory management efficiency.

[0052] For abnormal departments classified as highly abnormal departments, the consumables management measures taken are as follows: focus on monitoring the changes in the consumables demand of the department, and immediately issue a high-intensity warning, activate the emergency replenishment mechanism, prompt management personnel to take emergency replenishment measures, and quickly mobilize spare inventory resources, conduct a detailed analysis of the demand fluctuations of the department, and provide improvement plans.

[0053] For abnormal departments that are classified as highly abnormal departments, the consumables management measures taken are to focus on monitoring the changes in the consumables demand of the department, and immediately issue a high-intensity warning, start the emergency replenishment mechanism, prompt the management personnel to take emergency replenishment measures, quickly mobilize spare inventory resources, and conduct a detailed analysis of the demand fluctuations of the department, and provide improvement plans. Through advanced data analysis and anomaly detection algorithms, the system can analyze the demand fluctuations of the department in real time and automatically identify abnormal patterns. Once the demand fluctuation exceeds the preset high threshold, the system will immediately issue a high-intensity warning and start the emergency replenishment mechanism, automatically mobilize spare inventory and quickly execute the replenishment plan. At the same time, the system will analyze the causes of abnormal fluctuations, generate detailed reports, and propose improvement plans to help managers develop new inventory optimization measures. Through this rapid response mechanism, it can ensure that consumables can be replenished in time in highly abnormal situations to avoid affecting the normal operation of the department, and improve inventory management strategies in the long term to reduce the occurrence of similar problems.

[0054] Continuously monitor changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjust evaluation models and management strategies based on real-time data to optimize consumables management efficiency and reliability.

[0055] In order to continuously monitor the changes in the demand for consumables in abnormal departments and the effectiveness of their management measures, a real-time data collection and analysis platform can be established. First, the system needs to continuously collect data related to consumables demand from various departments, including daily consumption, replenishment, inventory, etc. By integrating Internet of Things (IoT) devices or connecting with hospital management systems, the real-time and comprehensive nature of the data can be ensured. Next, the data analysis module will continuously monitor these real-time data and evaluate the effectiveness of management measures, such as the timeliness of early warning responses and the accuracy of replenishment adjustments. The system can automatically identify possible deviations or deficiencies in the implementation of management measures and optimize the plan through data feedback. Real-time monitoring and data feedback can help managers quickly detect anomalies and take appropriate measures in a timely manner to ensure the stability of consumables management.

[0056] In order to dynamically adjust the evaluation model and management strategy according to real-time data, the system needs to introduce an adaptive learning and optimization mechanism. Specifically, the evaluation model can continuously self-correct according to the difference between historical data and real-time feedback. For example, when the change pattern of consumables demand fluctuates greatly, the system can analyze the new data trend through machine learning algorithms and adjust the original evaluation model. Whenever the system detects that the effect of management measures is lower than expected, it automatically adjusts the replenishment frequency, inventory management strategy and early warning threshold to ensure that it can adapt to demand fluctuations in a timely manner. In terms of specific implementation, an incremental model training method can be used to allow the system to continuously learn new data, reduce human intervention and improve efficiency. This dynamic adjustment mechanism can ensure that the evaluation model and management strategy always keep pace with actual demand changes and enhance the system's self-optimization capabilities.

[0057] Ultimately, through this continuous monitoring and dynamic adjustment, the goal is to optimize the efficiency and reliability of consumables management. This goal can be achieved through integrated optimization algorithms. The system can adjust resource allocation according to the specific changes in departmental needs and make real-time optimizations to replenishment strategies and inventory configurations. These optimizations are not only based on historical data, but are continuously iterated through algorithmic derivation and real-time data feedback. Through integrated optimization algorithms and automatic adjustment mechanisms, the system can effectively respond to various emergencies and avoid excessive manual intervention, thereby achieving more efficient and reliable consumables management. In addition, the dynamic adjustment evaluation model can help departments obtain the best resource allocation plan under different operating cycles and different consumables demand scenarios, ultimately improving the accuracy and reliability of overall consumables management.

[0058] like Figure 2The hemodialysis fistula puncture needle consumables management system shown includes a consumables demand fluctuation monitoring module, an abnormal department identification and marking module, an abnormal department data analysis module, an abnormal fluctuation assessment modeling module, a dynamic consumables management measures module, and a real-time monitoring and optimization adjustment module; The consumables demand fluctuation monitoring module detects the changes in the consumables demand of each department in real time during daily consumables management, and determines whether the changes in the consumables demand of each department conform to the regular fluctuation pattern based on historical data, daily fluctuation range and preset statistical standards; The abnormal department identification and marking module automatically marks departments as abnormal departments when it detects that the change trend of the consumables demand of departments does not conform to the regular fluctuation pattern; The abnormal department data analysis module obtains the consumables demand change information of all abnormal departments in real time, analyzes it after acquisition, and generates the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively; The abnormal fluctuation assessment modeling module builds an abnormal fluctuation assessment model for the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, generates the abnormal assessment coefficient of each abnormal department, and analyzes it after generation to assess the abnormal degree of the change in the consumables demand of each abnormal department, and divides each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the assessment results; Dynamic consumables management measures module, based on the classification results of each abnormal department, takes corresponding consumables management measures for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; The real-time monitoring and optimization adjustment module continuously monitors the changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjusts the evaluation model and management strategy based on real-time data to optimize the efficiency and reliability of consumables management.

[0059] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0060] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0061] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0062] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0063] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0066] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for managing consumables of hemodialysis fistula puncture needles, characterized in that: The specific steps include: In daily consumables management, the changes in consumables demand of each department are detected in real time, and based on historical data, daily fluctuation range and preset statistical standards, it is determined whether the changes in consumables demand of each department conform to the regular fluctuation pattern; When it is detected that the change trend of the consumables demand of some departments does not conform to the regular fluctuation pattern, these departments are automatically marked as abnormal departments; Obtain the consumables demand change information of all abnormal departments in real time, analyze it after acquisition, and generate the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively; An abnormal fluctuation assessment model is constructed for the demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, and the abnormal assessment coefficient of each abnormal department is generated. After the generation, the abnormal degree of the change in the consumables demand of each abnormal department is evaluated, and each abnormal department is divided into a highly abnormal department, a moderately abnormal department and a low abnormal department according to the evaluation results; According to the classification results of each abnormal department, corresponding consumables management measures are taken for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; Continuously monitor changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjust evaluation models and management strategies based on real-time data to optimize consumables management efficiency and reliability.

2. The hemodialysis fistula puncture needle consumables management method according to claim 1, characterized in that: Obtain the consumables demand change information of all abnormal departments in real time, analyze it after acquisition, and generate the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively, which specifically includes the following steps: Obtain the consumables demand change information of all abnormal departments in real time and perform pre-processing after acquisition; Extracting demand volatility measurement information and demand volatility analysis information from the pre-processed consumables demand change information of all abnormal departments; The extracted demand volatility measurement information and demand volatility analysis information are analyzed to generate the demand volatility sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department respectively.

3. The hemodialysis fistula puncture needle consumables management method according to claim 2, characterized in that: The logic for obtaining the demand fluctuation sensitivity coefficient of each abnormal department is as follows: Extract the demand volatility measurement information from the preprocessed consumable demand change information of all abnormal departments, including the number of consumables used in each abnormal department at different times within a period of time, the number of hemodialysis patients, and the total number of treatments for hemodialysis patients, and mark them as , and , Indicates that within a period of time Moment The number of consumables used in each abnormal department, Indicates that within a period of time Moment The number of hemodialysis patients in the abnormal department, Indicates that within a period of time Moment Total number of treatments for hemodialysis patients by abnormal departments, , , and All are positive integers; The mean of the number of consumables used in each abnormal department at different times during the time period, the mean of the number of hemodialysis patients, and the mean of the total number of treatments for hemodialysis patients are calculated. The specific calculation formula is as follows: In the formula, For different times in this time period The average number of consumables used in the abnormal departments, For different times in this time period The mean number of hemodialysis patients in each abnormal department, For different times in this time period The average number of treatments for hemodialysis patients in the abnormal departments; Calculate the demand fluctuation sensitivity coefficient of each abnormal department. The specific calculation formula is as follows: In the formula, For the The demand fluctuation sensitivity coefficient of each abnormal department.

4. The hemodialysis fistula puncture needle consumables management method according to claim 3, characterized in that: The logic for obtaining the abnormal fluctuation assessment index of each abnormal department is as follows: Extract the demand volatility analysis information from the preprocessed consumable demand change information of all abnormal departments, including the standard deviation of the consumable usage quantity of each abnormal department in the historical time period, the standard deviation of the number of hemodialysis patients, and the standard deviation of the consumable usage quantity of each abnormal department in the current time period, and mark them as , and , Indicates that in the historical period The standard deviation of the number of consumables used in the abnormal departments, Indicates that in the historical period The number of hemodialysis patients in the abnormal department, Indicates the number of The standard deviation of the number of consumables used in the abnormal departments, , is a positive integer; Calculate the abnormal fluctuation assessment index of each abnormal department. The specific calculation formula is as follows: In the formula, For the The abnormal fluctuation assessment index of each abnormal department.

5. The hemodialysis fistula puncture needle consumables management method according to claim 4, characterized in that: An abnormal fluctuation assessment model is constructed based on the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department to generate the abnormal assessment coefficient of each abnormal department, which specifically includes the following steps: The demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficients of several abnormal departments generated in the past period of time are collected and calibrated as , and , Indicates the demand fluctuation sensitivity coefficients, abnormal fluctuation assessment indexes and corresponding abnormal assessment coefficient numbers of several abnormal departments generated in the past period of time. , is a positive integer, and the data collected in the past period of time is formed into a historical data set; The multivariate regression model is selected as the abnormal fluctuation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: In the formula, , and is the regression coefficient; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of Using the final regression coefficient, the constructed abnormal fluctuation assessment model is input with the demand fluctuation sensitivity coefficient of each abnormal department generated in real time. and abnormal volatility assessment index , generate abnormal assessment coefficients of each abnormal department in real time .

6. The hemodialysis fistula puncture needle consumables management method according to claim 5, characterized in that: The abnormal evaluation coefficients of each abnormal department generated The pre-set abnormal evaluation coefficient threshold interval Compare and evaluate the abnormal degree of the change in consumables demand of each abnormal department according to the comparison results, and divide each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the evaluation results. The specific comparison analysis and division are as follows: like , the abnormal degree of the change in the consumables demand of the abnormal department is low, and the abnormal department is classified as a low-abnormal department; like , the abnormal degree of the change in the consumables demand of the abnormal department is moderate, and the abnormal department is classified as a moderately abnormal department; like The abnormal degree of the change in the demand for consumables in the abnormal department is high, and the abnormal department is classified as a highly abnormal department.

7. The hemodialysis fistula puncture needle consumables management method according to claim 6, characterized in that: According to the classification results of each abnormal department, corresponding consumables management measures are taken for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively, as follows: For abnormal departments classified as low-abnormal departments, the consumables management measures taken are: regularly monitor the changes in the consumables demand of the department to ensure the stability of its consumables management, and issue a mild warning to remind management personnel to pay attention to the demand situation of the department; For abnormal departments classified as moderately abnormal departments, the consumables management measures taken are: allocate consumables replenishment plans for the departments, and dynamically adjust the replenishment frequency and quantity based on real-time data to ensure that inventory management is adapted to demand fluctuations, and issue moderate warnings to prompt management personnel to strengthen monitoring and adjust inventory replenishment strategies based on historical data; For abnormal departments classified as highly abnormal departments, the consumables management measures taken are as follows: focus on monitoring the changes in the consumables demand of the department, and immediately issue a high-intensity warning, activate the emergency replenishment mechanism, prompt management personnel to take emergency replenishment measures, and quickly mobilize spare inventory resources, conduct a detailed analysis of the demand fluctuations of the department, and provide improvement plans.

8. A hemodialysis fistula puncture needle consumables management system, used to implement the hemodialysis fistula puncture needle consumables management method described in any one of claims 1 to 7, characterized in that: It includes a module for monitoring consumable demand fluctuations, a module for identifying and marking abnormal departments, a module for analyzing abnormal department data, a module for evaluating abnormal fluctuations, a module for dynamic consumable management measures, and a module for real-time monitoring and optimization adjustment; The consumables demand fluctuation monitoring module detects the changes in the consumables demand of each department in real time during daily consumables management, and determines whether the changes in the consumables demand of each department conform to the regular fluctuation pattern based on historical data, daily fluctuation range and preset statistical standards; The abnormal department identification and marking module automatically marks departments as abnormal departments when it detects that the change trend of the consumables demand of departments does not conform to the regular fluctuation pattern; The abnormal department data analysis module obtains the consumables demand change information of all abnormal departments in real time, analyzes it after acquisition, and generates the demand fluctuation sensitivity coefficient and abnormal fluctuation evaluation index of each abnormal department respectively; The abnormal fluctuation assessment modeling module builds an abnormal fluctuation assessment model for the generated demand fluctuation sensitivity coefficient and abnormal fluctuation assessment index of each abnormal department, generates the abnormal assessment coefficient of each abnormal department, and analyzes it after generation to assess the abnormal degree of the change in the consumables demand of each abnormal department, and divides each abnormal department into highly abnormal department, moderately abnormal department and low abnormal department according to the assessment results; Dynamic consumables management measures module, based on the classification results of each abnormal department, takes corresponding consumables management measures for highly abnormal departments, moderately abnormal departments and low abnormal departments respectively; The real-time monitoring and optimization adjustment module continuously monitors the changes in consumables demand in abnormal departments and the effectiveness of their management measures, and dynamically adjusts the evaluation model and management strategy based on real-time data to optimize the efficiency and reliability of consumables management.

Images