Intelligent clinical material management system

Abstract

The invention discloses an intelligent clinical material management system, and relates to the technical field of medical material management, and the system is characterized in that an Internet of Things sensing module is installed in a material storage area, environment parameters are updated in real time, and material counting authentication is carried out. When the materials flow, the sensing module identifies and authenticates the materials and then generates normal counting information. And the abnormal counting module processes data which are not passed or not authenticated, and abnormal counting information is generated. The first early warning module carries out inventory early warning identification in combination with the environment parameters and the counting information, and the second early warning module carries out further early warning based on an inventory demand prediction result. And the visual management module carries out overall early warning management according to the early warning result. The technical problems that due to the fact that an existing clinical material management system depends on manual counting, material counting is time-consuming and labor-consuming, errors are prone to occurring, and real-time and accurate tracking management of materials cannot be achieved are solved, and the technical effect of improving the efficiency and accuracy of inventory management is achieved.

Description

Technical Field

[0001] This application relates to the technical field of medical material management, and particularly to an intelligent clinical material management system. Background Art

[0002] With the continuous expansion of the scale of medical institutions and the increasing service demands, the management of clinical materials and consumables has become particularly important. Currently, most medical institutions rely on manual inventory taking, which is not only time-consuming and laborious but also prone to recording errors, resulting in inaccurate inventory management and low efficiency. Especially during ward rounds or large-scale inspections, higher precision requirements for the quantity of materials are needed, and manual inventory taking is difficult to meet the management needs of high efficiency and accuracy. With the development of medical informatization, the traditional manual management method has been difficult to meet the needs of modern medical institutions for efficient, accurate, and automated management tools.

[0003] In the related technologies at the present stage, there is a technical problem that the clinical material management system relies on manual inventory taking, resulting in time-consuming and laborious material inventory taking, being prone to errors, and being unable to achieve real-time and accurate tracking management of materials. Summary of the Invention

[0004] This application provides an intelligent clinical material management system, which solves the technical problem that the existing clinical material management system relies on manual inventory taking, resulting in time-consuming and laborious material inventory taking, being prone to errors, and being unable to achieve real-time and accurate tracking management of materials.

[0005] This application provides an intelligent clinical material management system, including:

[0006] Internet of Things (IoT) sensing module, which is set in the material storage area. An authentication unit and an identification and counting unit are integrated in the IoT sensing module for real-time updating of environmental parameters and counting authentication. The authentication unit is used to perform counting-assisted authentication, and the identification and counting unit is used for identification and counting; intelligent tag, which is set on the material. When there is material flow, the identification and counting unit of the IoT sensing module is used to perform corresponding intelligent tag identification, and after the authentication by the authentication unit is passed, normal counting information is generated; abnormal counting module, which is used to obtain the abnormal authentication data of the authentication unit. The abnormal authentication data includes data of failed authentication and unauthenticated data, and abnormal counting information is generated according to the abnormal authentication data; first warning module, which is used to read the normal counting information and the abnormal counting information, perform inventory warning identification through the environmental parameters, the normal counting information and the abnormal counting information, and establish a first warning identification result; second warning module, which is used to perform inventory demand prediction, and perform inventory warning identification on the normal counting information and the abnormal counting information by using the inventory demand prediction result, and establish a second warning identification result; visualization management module, which is used to perform warning management according to the first warning identification result and the second warning identification result.

[0007] It is intended to propose an intelligent clinical material management system through this application. First, an IoT sensing module is installed in the material storage area to update environmental parameters in real time and perform material counting authentication. Intelligent tags are equipped on the materials. When the materials flow, the sensing module identifies and authenticates them and then generates normal counting information. The abnormal counting module processes the data of failed or unauthenticated authentication and generates abnormal counting information. The first warning module combines environmental parameters and counting information to perform inventory warning identification, and the second warning module performs further warning based on the inventory demand prediction result. The visualization management module performs overall warning management according to the warning results. Through the automated real-time tracking management of clinical materials, the technical effects of improving the efficiency and accuracy of inventory management are achieved. Brief Description of the Drawings

[0008] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0009] Figure 1 It is a schematic structural diagram of the intelligent clinical material management system provided by the embodiment of this application;

[0010] Figure 2 It is a schematic structural diagram of the second warning module of the intelligent clinical material management system provided by the embodiment of this application.

[0011] Explanation of the accompanying drawings: Internet of Things sensor module 10, smart tag 20, abnormality counting module 30, first warning module 40, second warning module 50, visualization management module 60. DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides an intelligent clinical material management system, such as Figure 1 As shown, the system comprises:

[0016] The Internet of Things sensing module 10 is provided in the material storage area. The Internet of Things sensing module 10 integrates an authentication unit and an identification and counting unit, which are used to update environmental parameters and perform counting authentication in real time. The authentication unit is used to perform counting-assisted authentication, and the identification and counting unit is used to identify and count. Specifically, the Internet of Things sensing module 10 is installed at key positions in the clinical material storage area and initialized, and the sensors are calibrated to ensure accurate measurement of environmental parameters. The parameters of the authentication and identification and counting units are configured. Its built-in multiple environmental sensors continuously work, collect environmental data such as temperature, humidity, illuminance, and air quality at preset time intervals, and transmit them to the central database through wireless communication technology for real-time update, providing a basis for environmental control and material quality assurance. When there is a movement operation of the materials, the identification and counting unit of the Internet of Things sensing module 10 uses wireless identification technology to scan and read the intelligent tag information, uploads it to the authentication unit for legality verification. If it passes, the material flow is accurately counted, the relevant details are recorded and uploaded for inventory and flow management; if it fails, an alarm is triggered and the abnormal information is recorded and uploaded for subsequent investigation and handling, ensuring the safety and accuracy of material management and preventing illegal misappropriation, loss or misdelivery of materials.

[0017] The intelligent tag 20 is provided on the materials. When there is a material flow, the identification and counting unit of the Internet of Things sensing module 10 performs corresponding intelligent tag identification, and generates normal counting information after the authentication unit passes the authentication. Specifically, in the initial stage of clinical material management, each material is equipped with and attached with an intelligent tag 20 with key information such as material name, specification, model, production batch, production date, and expiration date, which is associated with the database of the material management system. When the materials flow in the storage area, the identification and counting unit of the Internet of Things sensing module 10 immediately emits a signal to scan and detect, interacts with the intelligent tag using technologies such as radio frequency identification, accurately reads its information after overcoming signal interference, and transmits it to the authentication unit. The authentication unit compares with the database according to the preset rules and permission system to check the compliance of the material operation process. If the authentication passes, the identification and counting unit generates normal counting information including material identification, flow time, quantity, operation type, and inventory update value according to the material flow direction and quantity change, and transmits it wirelessly to the central database of the material management system, providing a basis for inventory management, statistical analysis, and decision-making, and ensuring efficient and orderly material management.

[0018] The abnormal count module 30 is used to obtain the abnormal authentication data of the authentication unit. The abnormal authentication data includes unpassed authentication data and unauthenticated data, and generates abnormal count information according to the abnormal authentication data. Specifically, the abnormal count module 30 is closely connected to the authentication unit of the Internet of Things sensing module 10 and monitors its authentication status in real time. Once there is an unpassed authentication for material flow operations, such as not following the approval process, insufficient permissions, inconsistent label information with the database, or non-compliant material status, or an unauthenticated situation due to malfunctions of the Internet of Things sensing module 10, signal interference, label damage or loss, etc., the abnormal count module 30 immediately obtains the relevant data. Subsequently, the abnormal authentication data is classified and analyzed to analyze the specific reasons for unpassed authentication, such as personnel operation errors, permission management problems, etc., and the possible factors for unauthenticated situations, such as hardware failures, environmental factors or label problems, etc. Finally, abnormal count information including the occurrence time of the abnormality, material identification, abnormality type, cause and operation information is generated according to the analysis results, stored in the local cache in a standardized format, and uploaded to the central database of the material management system according to preset rules for management personnel to check and process in a timely manner to ensure the safety and accuracy of material management.

[0019] The first warning module 40 is used to read the normal count information and the abnormal count information, perform inventory warning identification through the environmental parameters, the normal count information and the abnormal count information, and establish a first warning identification result. Specifically, the first warning module 40 establishes a connection with the relevant database, reads the normal count information, abnormal count information and environmental parameters regularly or in real time, and integrates the data. Analyze the environmental parameters according to the preset material environmental suitability standards to judge whether the environment is suitable. If it exceeds the specified range, such as temperature affecting the activity of drugs, humidity causing equipment to get damp, etc., even if the inventory quantity is normal, a warning is triggered, and the potential risks are recorded and included in the warning identification result for taking environmental adjustment measures. At the same time, obtain the inventory dynamics reflected by the count information, master the material inbound and outbound rules and consumption speed by counting normally, analyze the abnormal count to find potential problems, comprehensively evaluate the inventory status in combination with the preset inventory warning rules, determine the warning signal and level type, and integrate the evaluation results. Finally, summarize and generate a structured first warning identification result, including the current status of the inventory materials, potential environmental risks, inventory dynamic trends, warning levels and recommended measures, and output it to the visualization management module 60 or management personnel in an intuitive way to help them understand the situation, make decisions, and ensure the efficient and safe management of materials.

[0020] In a possible implementation, the first warning module 40 further includes: an anomaly warning sub-module, which is used to perform trigger analysis on the anomaly count information according to a preset anomaly trigger threshold and establish an anomaly warning. Specifically, the anomaly warning sub-module first obtains the anomaly count information from the anomaly count module 30. The information covers relevant data on failed and uncertified material certifications and includes details of the anomaly events, such as the occurrence time, the material identification involved, and the reasons for the anomaly. Analysis is carried out based on the trigger thresholds preset by the system for different types of anomalies. For example, in the case of a failed material certification, if the number of failed certifications of a certain type of material reaches the preset threshold (e.g., 5 times) within a specific time period (e.g., 1 hour), it is determined that there may be a risk of abnormal operation. The anomaly warning sub-module will immediately establish an anomaly warning signal. The warning signal not only includes the basic information of the anomaly event but also grades the severity of the anomaly according to preset rules, such as minor anomaly, moderate anomaly, and severe anomaly, etc., so that managers can quickly understand the urgency and potential impact of the anomaly and take corresponding investigation and corrective measures, such as checking whether there are loopholes in the material management process, verifying the identity and permissions of the operators, etc., to prevent the recurrence of similar anomaly situations and ensure the safety and standardization of material management.

[0021] A flow warning sub-module, which is used to perform counting statistics on the normal count information and the anomaly count information and conduct trigger analysis on material flow warning based on the counting statistics results to establish a flow warning. Specifically, after collecting the normal count information and the anomaly count information from the Internet of Things sensing module 10, the flow warning sub-module performs comprehensive counting statistics on the data. For the normal count information, it statistically analyzes information such as the inbound and outbound quantities, frequencies, and flow directions of different materials in each time period, analyzes the flow trends and patterns of the materials. For example, it calculates the average daily outbound quantity of a certain high-value consumable in the past week and compares it with the historical data of the same period to observe whether there are abnormal fluctuations. For the anomaly count information, it focuses on statistically analyzing the number of anomaly events, the types and quantities of materials involved, etc., and evaluates the potential impact of the abnormal flow on the overall inventory. Through the counting statistics results and in combination with the preset material flow warning model, trigger analysis on material flow warning is carried out. For example, if the outbound quantity of a certain type of key material suddenly increases significantly within a short period of time, exceeding the normal fluctuation range, and at the same time there are anomaly count events (such as some materials are taken out despite failed certifications), it is determined that there may be a risk of material theft or management out of control. The flow warning sub-module will immediately establish a flow warning. The flow warning will detail the abnormal flow situation of the materials, including information such as the types, quantities, flow times, and directions of the materials involved, reminding managers to pay attention to the flow of the materials in a timely manner, take measures to verify the actual use and whereabouts of the materials, and strengthen inventory supervision to ensure the reasonable use of the materials and the accuracy of the inventory.

[0022] The environmental warning sub-module is used to identify environmental anomalies based on the environmental parameters and inventory distribution, establish environmental warnings, and establish the first warning identification result by using the anomaly warning, the flow warning, and the environmental warning. Specifically, the environmental warning sub-module first obtains the environmental parameters such as temperature, humidity, light intensity, air quality, etc. that are real-time monitored by the Internet of Things sensing module 10, as well as the inventory distribution information in the material management system, including the storage locations, storage quantities, and storage methods of different materials in the storage areas. Environmental anomaly identification is carried out based on the environmental parameters and inventory distribution. For example, for some drugs that are sensitive to temperature and humidity, a reasonable range of environmental parameters is set according to their storage requirements. If the temperature in a certain drug storage area exceeds the specified appropriate range for a long time, or the humidity rises sharply, it may affect the quality and shelf life of the drugs. At this time, the environmental warning sub-module will identify this area as an environmentally abnormal area. Considering the inventory distribution, if a large number of urgently needed drugs are stored in this area, the risk brought by the environmental anomaly will be more serious. Based on the environmental anomaly identification result, an environmental warning signal is established, which details information such as the occurrence area of the environmental anomaly, the abnormal parameter values, the types and quantities of materials that may be affected, etc. Finally, the environmental warning sub-module integrates the established environmental warning with the anomaly warning generated by the anomaly warning sub-module and the flow warning established by the flow warning sub-module to form a complete first warning identification result. The first warning identification result comprehensively reflects various potential risk situations in the material management process, including abnormal operations, abnormal flows, and the potential impact of environmental factors on the inventory, providing comprehensive and accurate warning information for managers, enabling them to formulate targeted countermeasures, such as adjusting the inventory layout, strengthening environmental control measures, investigating abnormal events, etc., to ensure the quality and supply stability of clinical materials.

[0023] In a possible implementation, the environmental warning sub-module further includes: a location parsing sub-module, configured to parse environmental parameters based on location signals to obtain the environmental location distribution. Specifically, the location parsing sub-module collaborates with the Internet of Things sensing module 10. The Internet of Things sensing module 10 is arranged with multiple sensor nodes with positioning functions in the material storage area. The nodes can collect location signals and corresponding environmental parameter information in real time, such as data on temperature, humidity, light intensity, etc. After receiving the raw data containing location and environmental parameters, the location parsing sub-module uses advanced signal processing algorithms and Geographic Information System (GIS) technology for parsing. By analyzing the intensity, direction of the location signals and the relative relationship with surrounding reference nodes, the precise three-dimensional coordinate positions of each data collection point in the material storage area are determined. The collected environmental parameters are associated and matched with the corresponding location information, thereby constructing the distribution of environmental parameters in the entire storage area, that is, obtaining the environmental location distribution. For example, in a large pharmaceutical warehouse, through the processing of the location parsing sub-module, it can be clearly known the temperature distribution in each corner of the warehouse, which areas have relatively stable temperatures, and which areas may have problems of too high or too low temperatures, providing a detailed spatial data basis for subsequent environmental analysis and warning.

[0024] An environmental adaptation sub-module, configured to input the environmental location distribution and the inventory distribution into an environmental adaptation model to generate an environmental warning. Specifically, the environmental adaptation sub-module obtains inventory distribution information from the material management system. The inventory distribution information details the storage locations and quantities of different types and batches of materials in the storage area. At the same time, it receives the environmental location distribution data generated by the location parsing sub-module, and takes these two sets of data as inputs and substitutes them into a pre-trained environmental adaptation model. The environmental adaptation model is constructed based on a large amount of historical environmental data, material storage characteristics, and actual environmental problem cases, and can simulate the influence relationship of different environmental conditions on the storage quality and safety of various materials. In the model, through the comprehensive analysis of the environmental location distribution and the inventory distribution, the environmental adaptation degree of each material storage area is evaluated. For example, if the model finds that a large number of precision medical devices sensitive to humidity are stored in a certain area, and the humidity in this area has been at a relatively high level and exceeds the safe range for a long time, it will determine that there is a relatively high environmental risk in this area. According to the output result of the model, the environmental adaptation sub-module generates environmental warning information. The warning information includes the types of materials that may be affected by the environment, the specific storage locations, the expected degree of environmental impact, and corresponding recommended measures, such as adjusting the ventilation equipment in this area, adding dehumidification devices, or considering transferring the materials to a more suitable storage location, etc., so as to prevent in advance the damage or quality decline of materials caused by environmental problems and ensure the effectiveness and availability of clinical materials.

[0025] The second warning module 50 is used to perform inventory demand forecasting, identify inventory warnings for the normal count information and the abnormal count information by using the inventory demand forecasting results, and establish a second warning identification result. Specifically, the second warning module 50 first collects data from various hospital information systems, including historical clinical data (covering past material usage and disease treatment information), hospital activity data (such as surgical arrangements, outpatient volume forecasts, etc.), and at the same time obtains the normal and abnormal count information of the Internet of Things sensing module 10. Feature extraction is carried out based on historical clinical data, data mining and statistical analysis methods are used to identify the material demand rules, and an inventory demand forecasting model (such as regression, machine learning model, etc.) is constructed and trained in combination with hospital activity data. Its performance and accuracy are ensured through cross-validation. Subsequently, information such as the current hospital activities is substituted into the model to calculate the future predicted demand value of materials, and factors such as the procurement cycle are analyzed and optimized. The predicted demand is compared with the actual inventory and replenishment volume, and inventory warnings are identified in combination with the normal and abnormal count information, classified and graded according to the shortage degree, abnormal severity and demand uncertainty. Finally, the inventory demand forecasting results, inventory status, abnormal situations, warning levels and recommended measures, etc. are summarized to form a second warning identification result, which is output to the visualization management module 60 or management personnel to help ensure the material supply and hospital operation.

[0026] In a possible implementation manner, as Figure 2 shown, the second warning module 50 further includes: a data calling sub-module, which is used to read historical clinical data and establish a historical clinical data set. Specifically, the data calling sub-module establishes a connection with the information system database of the hospital, and a large amount of historical clinical data is stored in this database, covering medical records of the past many years. The data calling sub-module accurately screens out the data related to clinical material usage from the database according to the preset data extraction rules and time range. For example, it will extract detailed data such as the drug lists prescribed for various diseases by different departments in each time period, the models and quantities of medical devices used, the diagnosis information of patients, and the treatment cycles. The data is integrated together to form a structured historical clinical data set, providing a rich and comprehensive data basis for subsequent analysis. During the extraction process, the data calling sub-module will also perform preliminary cleaning and sorting of the data, removing invalid or incorrect data records to ensure the quality and accuracy of the data set. For example, correcting typos in the data entry process, supplementing missing key information (such as drug specifications), etc., so that subsequent analysis can proceed smoothly and improve the reliability of the entire inventory demand forecasting.

[0027] The data analysis submodule is used to receive the historical clinical data set to extract data features and establish seasonal demand fluctuations. Specifically, after receiving the historical clinical data set from the data call submodule, the data analysis submodule uses a variety of data analysis techniques and algorithms to mine the potential laws therein. First, the time series analysis method is used to sort and analyze the data according to the time dimension to observe the trend of seasonal changes in the usage of different materials. For example, for drugs for the treatment of respiratory diseases, through the analysis of many years of data, it is found that its usage in winter is significantly higher than in other seasons, showing obvious seasonal fluctuation characteristics. The association rule algorithm in data mining is used to find the intrinsic connection between the use of materials and factors such as disease type and treatment method, and further determine which diseases or treatment plans will cause an increase or decrease in the demand for specific materials. Through analytical means, the data analysis submodule extracts the seasonal demand fluctuation law of various materials and quantifies it into a specific mathematical model or statistical indicator, such as calculating the average demand growth rate of each material in different seasons, the approximate time range of the peak and trough periods of demand, etc., to provide key seasonal factor references for inventory demand forecasting, so that the forecast results can better adapt to the seasonal changes in actual clinical needs and avoid inventory backlogs or out-of-stock situations caused by seasonal factors.

[0028] The activity identification submodule is used to identify hospital activity data and establish activity requirements based on the hospital activity data. Specifically, the activity identification submodule focuses on collecting and analyzing various types of activity data in the hospital. The data sources are wide-ranging, including the hospital's surgery scheduling system, outpatient appointment system, special medical project development plan, and various meeting notices and activity schedules within the hospital. The activity identification submodule identifies various types of activity information that may affect clinical material demand through real-time monitoring and data capture of these data sources. For example, when it is detected that a department plans to carry out a series of high-difficulty operations in the next week, the activity identification submodule will analyze in detail the medical equipment and special consumables required for these operations, and combine the estimated duration of the operation, the number of patients involved, and other factors to establish an activity demand model for the activity. The model not only takes into account the direct material consumption required for the operation itself, but also analyzes the possible demand for spare materials, materials required for postoperative care, and materials required for other related treatments that may be caused by the operation. Through comprehensive identification and accurate analysis of various hospital activities, the activity identification submodule can predict in advance the additional material demand that the activities will bring, and provide timely and accurate references to activity-related factors for inventory demand forecasting, ensuring that the hospital has sufficient supply of materials during various activities and ensuring the smooth progress of medical services.

[0029] The forecasting sub-module is used to establish the inventory demand forecasting results based on seasonal demand fluctuations and event demands. Specifically, the forecasting sub-module receives the seasonal demand fluctuation information from the data analysis sub-module and the event demand information from the event identification sub-module, takes the key factors as the main input variables, combines the current inventory level, material procurement cycle, the supply capacity of suppliers, and other external factors that may affect material supply (such as market price fluctuations, policy and regulation changes, etc.), and uses advanced forecasting models and algorithms (such as multiple linear regression models, neural network models, seasonal autoregressive integrated moving average models, etc.) to perform inventory demand forecasting calculations. For example, in the multiple linear regression model, the seasonal demand fluctuation indicators, various event demand variables, and other relevant factors are used as independent variables, and the inventory demand is used as the dependent variable. Through the training and fitting of historical data, the weight relationship between the variables is determined, thus establishing a mathematical forecasting model between the inventory demand and the factors. Using this model, the forecasting sub-module can calculate the corresponding inventory demand forecasting results according to different future scenario assumptions (such as different event scales, seasonal change intensities, etc.). These results not only include the specific demand quantities of various materials in a future period (such as one month, one quarter, or half a year), but also cover the uncertainty range and confidence interval of the demand, providing a comprehensive, scientific, and forward-looking basis for the hospital's inventory management decision-making. Hospital administrators can formulate reasonable procurement plans, adjust inventory strategies, optimize material distribution plans, etc. based on these forecasting results to ensure that the inventory level of clinical materials always remains within a reasonable range that can meet clinical needs and avoid resource waste, improving the hospital's operational efficiency and medical service quality.

[0030] The Visualization Management Module 60 is used to perform early warning management based on the first early warning recognition result and the second early warning recognition result. Specifically, the Visualization Management Module 60 is first connected in real time with the First Early Warning Module 40 and the Second Early Warning Module 50, receives and integrates and preprocesses the data of the first early warning recognition result (including inventory status, environmental risks, counting trends, early warning levels and measures, etc.) and the second early warning recognition result (covering inventory demand forecasting, etc.) to ensure accuracy and completeness. Then, based on this, it designs and constructs an intuitive and clear visualization display interface containing elements such as charts, graphs, maps, and dashboards. For example, a bar chart is used to present the comparison between inventory and thresholds, a line chart is used to show the trend of inbound and outbound flows, a heat map is used to display the distribution of environmental parameters, and a dashboard is used to indicate the early warning level. An information area is also set up to facilitate viewing of material and early warning details. At the same time, an audible and visual early warning system is integrated, and parameters are configured according to the early warning level. A low-frequency beep and a yellow light are used for mild cases, an intermittent high-frequency beep and an orange light are used for moderate cases, and a rapid high-frequency alarm and a red light are used for severe cases, which cooperate with the visualization interface to ensure a quick response. In addition, by integrating with the hospital communication system, early warning information containing a brief description, level, and details link is pushed to relevant personnel according to the preset list and rules, and the push history and feedback situation are recorded to optimize the notification mechanism, achieve all-round early warning management, and ensure the efficient and safe management of material supply.

[0031] In a possible implementation manner, the Visualization Management Module 60 further includes: an early warning sub-module, which is used to perform early warning trigger analysis of preset thresholds on the first early warning recognition result and the second early warning recognition result, and report early warning alarms according to the trigger level. Specifically, the early warning sub-module first establishes a data communication link with the First Early Warning Module 40 and the Second Early Warning Module 50, obtains and integrates the data of inventory, inbound and outbound, environmental parameters, demand forecasting, and early warning information in the first early warning recognition result and the second early warning recognition result to ensure that the data formats are standard and consistent. Then, according to the actual needs, experience, and standard specifications of clinical material management, preset thresholds are set for early warning indicators such as inventory quantity, environmental parameters, and demand forecasting deviation rate, and factors such as material importance and supply stability are comprehensively considered, and an early warning trigger model is constructed using statistical analysis and machine learning algorithms. After that, the data is continuously monitored and analyzed, the real-time data is compared with the thresholds and then input into the model, and the early warning trigger level is determined considering factors such as the degree of deviation and duration. For example, if the material inventory is lower than the safety inventory but has not reached the replenishment point and there is no serious shortage in the short term, a mild early warning may be triggered; if the inventory drops sharply and approaches the emergency shortage threshold and there are abnormal situations, a severe early warning is triggered. Once the trigger level is determined, the early warning sub-module reports early warning alarms through various methods such as flashing icons on the visualization interface, text messages, emails, and broadcasts according to the level. At the same time, a feedback mechanism is established to record the response time, measures, and resolution status to optimize early warning management and ensure the stable supply of materials and the orderly operation of the hospital.

[0032] In a possible implementation, the system further includes: a cycle counting module for performing cycle counting on materials. When materials flow out, outflow counting is performed based on the unique identifier of the outflowing materials. When the outflowing materials are returned, inflow counting is generated, and cycle counting is completed based on the outflow counting and the inflow counting. Specifically, the cycle counting module closely cooperates with the Internet of Things sensing module 10. When materials flow out of the storage area, the sensing module's identification and counting unit detects the movement of the materials and reads the unique identifier of its smart label. After receiving it, the cycle counting module records information such as the outflow time, quantity, and destination in the outflow counting database table to achieve accurate outflow counting, facilitate tracing the flow direction, and troubleshoot problems. When the materials are returned, the unique identifier is obtained again by relying on the sensing module. The cycle counting module adds records such as the inflow time, quantity, and return source in the inflow counting database table, verifies the inflow logic, checks the status of the materials, and remarks abnormalities to ensure the accuracy and completeness of the inflow counting. The cycle counting result is calculated in real time based on the outflow and inflow counting records, the cycle counting status of the materials in the inventory management system is updated, and it is fed back to modules such as inventory statistics and early warning to provide a basis for procurement plans and inventory management decisions, ensure the stable supply and efficient utilization of materials, and improve the operation efficiency and reliability of the system.

[0033] In a possible implementation, the system further includes: an intelligent interaction module for providing an interaction entry, reading the stored data in the central database, and viewing the status of materials. The central database records the storage information of materials, including material name, specification, quantity, location, and environmental parameters. Specifically, the intelligent interaction module presents an interaction interface at the user end. After the user logs in, it establishes a secure and stable connection with the central database through an encryption and authentication mechanism. Then, according to the user operation instruction, a precise query statement is generated, and status information such as material name, specification, quantity, location, and environmental parameters is extracted according to the user's permissions. The central database returns the qualified data in a structured format, and the intelligent interaction module converts it into an intuitive and visual form for presentation. For example, the basic information of materials is displayed in a table, and the quantity trend and environmental parameter distribution are presented in a chart. During this period, the intelligent interaction module also provides interaction functions such as sorting, filtering, and searching. If the user finds problems with the material information, they can directly submit feedback, and the module records and forwards it to relevant personnel for timely verification and processing, so as to maintain the accuracy and timeliness of the system, optimize the management process, and ensure the material supply.

[0034] In a possible implementation, the system further includes an allocation optimization module, which is used to call an image recognition sensor to perform real-time image acquisition of clinical requirements, establish a real-time image data set, perform temporal requirement analysis of the real-time image data set through a deep learning channel, establish a temporal requirement analysis result, and if a priority allocation command is triggered, optimize the material allocation according to the temporal requirement analysis result and the real-time inventory, establish an optimization result, and manage the material flow according to the optimization result. Specifically, the allocation optimization module first communicates with the image recognition sensor in the clinical area to start image acquisition. The high-resolution sensor captures images of the patient's condition, the status of medical staff, and the usage of medical equipment in real time. The module sorts and classifies them, extracts effective features, and establishes a real-time image data set as the data source for clinical requirement analysis. Then the data set is input into a pre-trained deep learning channel. Based on the convolutional neural network and recurrent neural network architectures, features are extracted through multiple layers of convolution and pooling, and then the recurrent neural network analyzes the temporal changes of the features to parse the dynamic law of clinical requirements over time, obtaining the temporal requirement analysis result. When a priority allocation command is triggered due to major emergencies, critical material shortages, or urgent needs of specific patient groups, etc., the module uses optimization algorithms such as linear programming to optimize based on the temporal requirement analysis result and the real-time inventory, considering constraints such as supply capacity, demand priority, and transportation cost, to obtain the optimization result of material allocation. Finally, material flow management instructions are generated in sequence, including the allocation path, transportation method, target department, and delivery time, etc., and are transmitted to relevant personnel through the information system. The logistics distribution department transports according to the instructions and monitors in real time, and the receiving personnel provide acceptance feedback. The module will also dynamically optimize and adjust according to the actual situation to ensure stable material supply and the smooth progress of medical work.

[0035] In the embodiments of the present application, an IoT sensing module is installed in the material storage area to update environmental parameters in real time and perform material counting authentication. Smart tags are equipped on the materials. When the materials flow, the sensing module identifies and authenticates them to generate normal counting information. The abnormal counting module processes the data that fails to pass or is not authenticated to generate abnormal counting information. The first warning module combines environmental parameters and counting information to perform inventory warning identification, and the second warning module performs further warning based on the inventory demand prediction result. The visualization management module performs overall warning management according to the warning result, and through the automated real-time tracking management of clinical materials, achieves the technical effect of improving the efficiency and accuracy of inventory management.

[0036] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0037] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recited in the present application can be executed in an order different from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. Intelligent clinical material management system, characterized by: The system comprises: An Internet of Things sensor module, which is arranged in a material storage area and has an authentication unit and an identification and counting unit integrated therein, for real-time updating of environmental parameters and counting authentication, wherein the authentication unit is used to perform counting auxiliary authentication, and the identification and counting unit is used to identify and count; Smart tags, which are set on materials. When there is material flow, the identification and counting unit of the Internet of Things sensor module is used to perform corresponding smart tag identification, and after the authentication unit passes the authentication, normal counting information is generated; An abnormality counting module, used for obtaining abnormal authentication data of the authentication unit, wherein the abnormal authentication data includes authentication failure data and unauthenticated data, and generating abnormality counting information according to the abnormal authentication data; A first warning module, configured to read the normal counting information and the abnormal counting information, perform inventory warning identification based on the environmental parameters, the normal counting information and the abnormal counting information, and establish a first warning identification result; A second warning module is used to perform inventory demand forecasting, use the inventory demand forecasting result to perform inventory warning identification on the normal counting information and the abnormal counting information, and establish a second warning identification result; A visualization management module is used to perform warning management based on the first warning identification result and the second warning identification result.

2. The intelligent clinical material management system according to claim 1, characterized in that: The first warning module includes: The abnormal warning submodule is used to trigger the analysis of the abnormal count information according to the preset abnormal trigger threshold and establish an abnormal warning; A flow warning submodule is used to count and count the normal counting information and the abnormal counting information, and to perform material flow warning trigger analysis based on the counting and statistical results to establish a flow warning; The environmental warning submodule is used to identify environmental anomalies according to the environmental parameters and inventory distribution, establish environmental warnings, and use the abnormal warnings, flow warnings and environmental warnings to establish a first warning identification result.

3. The intelligent clinical material management system according to claim 2, characterized in that: The environmental early warning submodule includes: The location analysis submodule is used to analyze environmental parameters based on the location signal and obtain the environmental location distribution; The environmental adaptation submodule is used to input the environmental location distribution and the inventory distribution into the environmental adaptation model to generate an environmental warning.

4. The intelligent clinical material management system according to claim 1, characterized in that: The second early warning module comprises: The data calling submodule is used to read historical clinical data and establish a historical clinical data set; A data analysis submodule, for receiving the historical clinical data set to extract data features and establish seasonal demand fluctuations; An activity identification submodule, used to identify hospital activity data and establish activity requirements based on the hospital activity data; The forecasting submodule is used to establish inventory demand forecast results based on seasonal demand fluctuations and event demand.

5. The intelligent clinical material management system according to claim 1, characterized in that: The visual management module includes: The early warning submodule is used to perform early warning trigger analysis of the first early warning identification result and the second early warning identification result at a preset threshold, and issue an early warning alarm according to the trigger level.

6. The intelligent clinical material management system according to claim 1, characterized in that: The system further comprises: The circulation counting module is used to count the circulation of materials. When materials flow out, the outflow count is performed according to the unique identification of the outflow materials. When the outflow materials are returned, the inflow count is generated, and the circulation counting is completed according to the outflow count and the inflow count.

7. The intelligent clinical material management system according to claim 1, characterized in that: The system further comprises: The intelligent interaction module is used to provide an interaction entrance and read the storage data of the central database to check the status of materials. The central database records the storage information of materials, including material name, specification, quantity, location, and environmental parameters.

8. The intelligent clinical material management system according to claim 1, characterized in that: The system further comprises: The allocation optimization module is used to call the image recognition sensor to collect real-time images for clinical needs, establish a real-time image data set, perform timing demand analysis of the real-time image data set through a deep learning channel, and establish timing demand analysis results. If a priority allocation command is triggered, material allocation is optimized based on the timing demand analysis results and real-time inventory, an optimization result is established, and material flow management is performed based on the optimization result.

Images