A hospital consumable inventory risk early warning method, system, device and medium

Abstract

The application relates to a hospital consumable inventory risk early warning method, system, device and medium, and belongs to the technical field of hospital risk control management, which comprises the following steps: according to the next day's operation scheduling, a consumable standard set is applied for, and after the inventory is confirmed, the set is marked as planned and is associated with operation information; after the set is taken, all components in the set are marked as taken, virtual sub-records are created for the components, and the initial state is set as unused in the set. After the operation is completed, the bar code of the used components is scanned, the used components are marked as consumed and the time stamp is recorded; the bar code of the unused components is scanned, the unused components are marked as recyclable and the return process is triggered. Past N-day closed set records are regularly analyzed, the idle rate of key components is calculated, if the idle rate exceeds the threshold, an idle signal is generated, it is marked that there is a systematic idle risk and the storage information is obtained, whether there is an inventory backlog risk is judged according to the storage information, and if yes, a backlog early warning is generated. The application has the beneficial effects of improving the fine degree and risk prevention and control capability of hospital consumable inventory management.

Description

Technical Field

[0001] This application relates to the technical field of hospital risk management, and in particular to a method, system, equipment and medium for early warning of hospital consumable inventory risks. Background Technology

[0002] In the daily operations of a hospital, consumable inventory management is a crucial task. As an important component of medical services, the proper stockpiling and effective use of medical consumables directly affect the hospital's medical quality and operating costs. With the continuous development of medical technology and the increasing number of surgeries, hospitals' needs for consumables are becoming increasingly diverse and complex.

[0003] Currently, hospital consumable inventory management primarily relies on traditional inventory ledger management, supplemented by basic information systems. Typically, clinical departments submit consumable requisition plans periodically based on historical usage experience. The inventory management department then checks the current inventory against the requisition requests. If the inventory meets the demand, the requisition is processed; otherwise, the procurement process is initiated. For surgical consumables, a model of pre-operative requisition and post-operative verification is often adopted. This involves manual recording of consumable receipts and usage, and regular comprehensive inventory checks to compile data such as remaining inventory and total consumption. When the inventory level falls below a preset safety stock threshold, the system automatically generates a replenishment reminder. When the inventory level significantly exceeds regular consumption needs, management experience is used to assess the risk of overstocking and adjust the procurement plan accordingly.

[0004] While the above-mentioned conventional technical solutions can meet the basic needs of consumable inventory management, the disconnect between consumable requisition and clinical demand can easily lead to excessive requisition and inventory backlog, or insufficient requisition and shortage of consumables during surgery. Furthermore, since only simple replenishment reminders are given based on inventory quantity thresholds, systemic risks of idle stock and potential backlogs cannot be identified, resulting in weak risk control capabilities for hospital consumable inventory. Summary of the Invention

[0005] To improve the sophistication of hospital consumable inventory management and risk control capabilities, this application provides a method, system, equipment, and medium for early warning of hospital consumable inventory risks.

[0006] Firstly, this application provides a method for early warning of inventory risks in hospital consumables, employing the following technical solution: A method for early warning of inventory risks in hospital consumables includes: According to the surgery schedule for the next day, the corresponding standard package of consumables is requested, and when it is confirmed that the standard package of consumables is in stock, the status is updated to "planned" and associated with the surgery information, including the planned surgery time, operating room, and surgeon ID; After the standard consumable kit is physically claimed, the status is updated to claimed, and a virtual sub-record is created for all components within the standard consumable kit. The initial status of each component is set to unused in the kit. After the operation, scan the unique serial number barcode of each used component, update the status of the corresponding component to consumed, and record the consumption timestamp; scan the unique serial number barcode of each unused component, update the status of the corresponding component to unused and recyclable, and trigger the component return process; Regularly analyze all package records that have been closed in the past N days, calculate the idle rate of key components, and when the idle rate is greater than the idle threshold, generate an idle signal, mark the corresponding component as having a systemic idle risk, and obtain the corresponding inbound information; Based on the warehousing information, determine whether there is a risk of inventory backlog; if so, generate a backlog warning.

[0007] By adopting the above technical solutions, from a clinical operations perspective, by linking consumable requisition with surgical information, starting with the next day's surgical scheduling, the accurate supply of consumables required for surgery is ensured, avoiding delays due to consumable shortages. Furthermore, through real-time updates of kit status and component-level full lifecycle tracking, the flow of each consumable is traceable, improving the standardization and transparency of clinical consumable use and reducing confusion in intraoperative consumable management. From an inventory management perspective, this breaks away from the traditional extensive inventory management model. Postoperative scanning records of component usage status clearly distinguish between consumed, unused, and recyclable consumables, providing accurate data for consumable recycling and inventory write-offs, avoiding unnecessary waste. Regular analysis of historical kit records to calculate the idle rate of key components, combined with incoming information to assess inventory backlog risks, can proactively identify systemic inventory problems, helping hospitals optimize inventory structure, reduce capital tied up in inventory and consumable expiration losses, and achieve dynamic inventory balance. This solution improves the precision of hospital consumable inventory management and risk control capabilities by constructing a closed-loop management mechanism that runs through the entire process from preoperative application, intraoperative circulation, and postoperative analysis, and realizes the transformation from passive response to proactive early warning.

[0008] Optionally, the hospital consumables inventory risk warning method further includes: When an emergency request for a component is received during operation, check if there is available inventory of the corresponding component; If yes, a delivery task is generated based on the surgical information; otherwise, a stockout signal is generated. Based on the out-of-stock signal, an emergency search is performed, which includes finding alternative models, searching for in-transit inventory, transferring across hospital campuses, and contacting suppliers for emergency direct delivery. The search results are integrated to generate an emergency decision dashboard, which is then pushed to the operating room.

[0009] By adopting the above technical solutions, in clinical surgical scenarios, sudden shortages of surgical consumables often directly affect the surgical process and even patient safety. This process addresses this by establishing a rapid-response emergency requisition channel, which can complete inventory retrieval immediately upon receiving a request. If available inventory is available, it directly links the surgical information to generate a delivery task, minimizing the response time for consumable delivery and providing timely support for the smooth progress of the surgery. When inventory is critically low, the system automatically triggers a multi-dimensional emergency search, from alternative models and in-transit inventory to inter-hospital transfers and emergency direct delivery from suppliers, comprehensively exploring all possible consumable replenishment channels. The scattered search results are integrated into an intuitive emergency decision-making dashboard and pushed to the operating room, allowing medical staff to make the best choice quickly based on the dashboard information without spending time coordinating resources themselves, thus alleviating the pressure caused by sudden intraoperative situations.

[0010] Optionally, the hospital consumables inventory risk warning method further includes: After the surgery where an emergency claim event occurred, review all package consumption records containing emergency claim components within M days. If multiple instances of urgently requested components are found to be in the state of consumed, but other critical components within the same package are in the state of unused and recyclable, then a related event record representing isolated shortages accompanied by idleness is generated.

[0011] By adopting the above technical solutions, in actual clinical practice, single events of emergency intraoperative requisitions are often easily regarded as isolated incidents. However, by retrospectively analyzing the consumption records of related consumable kits within M days, systemic problems hidden behind isolated events can be discovered. When multiple emergency-requisitioned components have been consumed, but other key components within the same kit are in an unused and recyclable state, this "isolated shortage accompanied by idleness" related event precisely exposes the core contradiction of the mismatch between the standard consumable kit configuration and the actual surgical needs. This may be due to redundant kit component settings, or the failure to accurately identify the differences in component requirements for different surgeries. By generating such related event records, hospitals can move beyond the limitations of single events and re-examine the rationality of consumable kits from a global perspective, providing data support for the dynamic optimization of kits. This reduces unnecessary idleness and sudden shortages of consumables from the source, making consumable configuration more aligned with actual clinical needs and further reducing the risk of inventory backlog and shortages.

[0012] Optionally, the hospital consumables inventory risk warning method further includes: After the surgery in which an emergency requisition event occurs, the surgeon's deviation from the usual practice for this surgery, the first usage rate of the unused recyclable component, and the second usage rate of the emergency requisition component that can replace the unused recyclable component are calculated. If the second usage rate is not less than k times the first usage rate and the habit deviation is below the threshold, it is marked as an abnormal consumption event.

[0013] By adopting the above technical solution, it is possible to identify the correlation between physician operation behavior and consumable usage, given that different surgeons often have different surgical habits in clinical practice. This directly affects the type and frequency of consumable usage. This step, after the surgery where an emergency requisition event occurs, calculates the surgeon's habit deviation, the first usage rate of unused recyclable components, and the second usage rate of emergency requisition components. When the second usage rate is not less than k times the first usage rate and the habit deviation is below a threshold, it is marked as an abnormal consumption event. This effectively identifies unreasonable situations where "physicians, while adhering to their own operating habits, extensively use replaceable emergency requisition components, leaving the original components in the kit idle." Such situations often conceal the risk of wasted consumable usage or a mismatch between the kit component configuration and the physician's personal operating habits. By marking and analyzing these abnormal consumption events, hospitals can more accurately identify hidden waste in the use of consumables, communicate with doctors to optimize operating habits, and provide a basis for the personalized configuration of consumable kits. This allows the kits to meet the needs of general surgeries while adapting to the operating habits of different doctors, thereby minimizing the unreasonable use and idleness of consumables while ensuring the smooth progress of surgery, and further reducing inventory backlog and cost waste.

[0014] Optionally, the hospital consumables inventory risk warning method further includes: After generating a record of associated events representing isolated shortages accompanied by idleness, or after marking an anomalous consumption event, retrieve the clinical event calendar within 24 hours before and after the anomalous signal event point; Determine whether there are preset high-risk clinical event tags in the clinical event calendar. The high-risk clinical event tags include intraoperative complications, temporary changes in surgical procedures, and emergency surgical intervention. If yes, mark the associated event record or the abnormal consumption event as a clinically reasonable variant and remove the corresponding risk warning; if no, confirm the management abnormality and trigger configuration optimization suggestions for the corresponding component or package.

[0015] By adopting the above technical solution, it is found that relying solely on data indicators to determine anomalies in inventory risk warning management often has limitations and can easily overlook unforeseen objective factors during clinical surgery. By introducing a clinical event calendar for cross-validation, it is possible to effectively distinguish between "reasonable consumption deviations caused by treatment needs" and "abnormal consumption caused by mismanagement." When high-risk clinical events such as intraoperative complications or changes in surgical procedures are detected, the system intelligently identifies them as clinically reasonable variations and exempts them from warnings. This respects the principle of "patient safety first" in medical practice, avoids misjudging and interfering with doctors' emergency response actions, and reduces the push of invalid warning information. Conversely, when objective clinical factors are excluded, the system identifies them as management anomalies, ensuring the relevance and effectiveness of subsequent inventory configuration optimization suggestions.

[0016] Optionally, the specific steps for triggering configuration optimization suggestions for the component or suite include: Identify the type of abnormal signal; If the event is to characterize the associated event of isolated shortage accompanied by idleness, then the component consumption matrix of the standard package of consumables is statistically analyzed within a preset period, and the frequency of emergency requisition of shortage components and the unused rate of idle components are calculated. Based on the frequency of emergency applications, incremental configuration suggestions for the shortage components are generated, and suggestions for reducing or eliminating the idle components are generated based on the unused rate. These suggestions are then combined to generate a package structure reorganization scheme. If it is an abnormal consumption event, the components urgently requested during the operation are extracted as preferred components, and the original components in the same package that are unused, recyclable, and have similar functional attributes to the preferred components are locked. Based on the surgeon's ID, their historical surgical preference data is obtained, and a personalized demand model for the physician is constructed. The personalized demand model for the physician is used to represent the physician's preference weight vector for different specification attribute components. The attribute features of the preferred components are input into the physician's personalized needs model to obtain the preference fit for the corresponding surgeon. If the preference fit is greater than the preset fit threshold, it is determined that the preferred component matches the long-term preference characteristics of the corresponding surgeon, and a customized package configuration suggestion is generated for the surgeon, replacing the original component with the preferred component.

[0017] By adopting the above technical solutions, differentiated and precise optimization strategies are provided for different types of inventory risk signals. For situations of "isolated shortages accompanied by idleness," the degree of shortage and idleness is quantified to directly guide the reorganization of the kit structure, resolving the structural contradiction of mismatch between kit configuration and routine surgical needs, and achieving a dynamic balance of inventory resources. For "abnormal consumption events," a personalized physician demand model is constructed and its preference fit is calculated, transforming a single emergency requisition behavior into a quantifiable preference feature verification process. This filters out interference from accidental operations, ensuring that only components with high fit under model verification are included in the dedicated kit. This achieves an organic combination of the universality of standard kits and the specificities of physician operations, improving the level of precision in consumable management.

[0018] Optionally, the hospital consumables inventory risk warning also includes: After generating package configuration optimization suggestions, the component attribute types are distinguished, including common components and personalized components; For the aforementioned common components, historical consumption data of all physicians in the hospital are aggregated to generate a hospital-wide total volume forecast procurement order; For the personalized component, the surgical schedule within the future preset period is scanned, the planned number of surgeries for a specific surgeon is extracted, and the expected demand is calculated by combining the historical consumption rate of the target component corresponding to the specific surgeon. A purchase requisition form with a physician-reserved label is generated based on the expected demand.

[0019] By adopting the above-mentioned technical solutions, a hierarchical and categorized intelligent replenishment mechanism has been constructed, transforming traditional extensive procurement into precise procurement based on actual clinical needs. For common components, hospital-wide aggregated forecasting ensures basic supply efficiency; for personalized components, combining future surgical schedules with physicians' individual consumption habits enables precise replenishment tailored to each patient. This avoids shortages due to insufficient general inventory for physicians' personalized needs, while also preventing inventory backlogs caused by blind bulk purchasing.

[0020] Secondly, this application provides a hospital consumables inventory risk early warning system, which adopts the following technical solution: A hospital consumables inventory risk early warning system includes: The consumables requisition module is used to requisition the corresponding standard packages of consumables based on the surgical schedule for the next day. The status processing module is used to update the status to "planned" when it is confirmed that the standard consumable kit is in stock, and associate it with surgical information, including the planned surgical time, operating room, and surgeon ID. It is also used to update the status to "received" after the standard consumable kit is physically retrieved, and to create a virtual sub-record for all components in the standard consumable kit. The initial status of each component is set to "in package, unused". The scanning module is used to scan the unique serial number barcode of each used component and the unique serial number barcode of each unused component after the operation; the status processing module updates the status of the corresponding component to consumed and records the consumption timestamp, and updates the status of the corresponding component to unused and recyclable, and triggers the component return process; The package record analysis module is used to periodically analyze all package records that have been closed in the past N days, calculate the idle rate of key components, generate an idle signal when the idle rate is greater than the idle threshold, mark the corresponding component as having a systemic idle risk, obtain the corresponding inbound information, and also use the inbound information to determine whether there is an inventory backlog risk; if so, generate a backlog warning.

[0021] Thirdly, this application provides a computer device that adopts the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the hospital consumables inventory risk warning method as described in the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the first aspect, a method for early warning of hospital consumable inventory risks.

[0023] In summary, this application includes at least one of the following beneficial technical effects: From precise requisition of consumables for preoperative surgical scheduling to multi-channel emergency replenishment for emergency requisition during surgery, and then to full lifecycle tracking and multi-dimensional data analysis of postoperative consumables, a digital management and control closed loop covering the entire process of consumable circulation has been formed. This has promoted the transformation of hospital consumables management from passively responding to problems to proactively warning and intervening in advance, and improved the foresight and accuracy of inventory risk prevention and control.

[0024] Breaking away from the limitations of traditional inventory management that only focuses on the "flow of goods," this approach incorporates human factors such as physicians' operating habits and clinical emergencies into its analysis. While ensuring the needs of general surgeries, it adapts to the operating habits of different physicians, minimizing the unreasonable use and idleness of consumables, and achieving an organic balance between standardized management and personalized needs.

[0025] By developing differentiated procurement strategies for consumable components with different attributes, we can avoid shortages of personalized needs caused by insufficient general inventory, and also prevent inventory backlog caused by blind procurement, thereby reducing the hospital's operating costs. Attached Figure Description

[0026] Figure 1 This is a first flowchart of an embodiment of the method of this application; Figure 2 This is a second flowchart of an embodiment of the method of this application; Figure 3 This is a third flowchart of an embodiment of the method of this application; Figure 4 This is the fourth flowchart of an embodiment of the method of this application; Figure 5 This is the fifth flowchart of an embodiment of the method of this application; Figure 6 This is the sixth flowchart of an embodiment of the method of this application. Detailed Implementation

[0027] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-6 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0028] The first embodiment of this application discloses a method for early warning of inventory risks in hospital consumables. (Refer to...) Figure 1 The risk warning method includes S110-S150: S110: Based on the surgical schedule for the next day, apply for the corresponding standard consumable package, and when it is confirmed that the standard consumable package is in stock, update the status to "planned" and associate it with the surgical information, including the planned surgical time, operating room, and surgeon ID. S120: After the standard consumable kit is physically claimed, update the status to claimed and create a virtual sub-record for all components in the standard consumable kit. The initial status of each component is set to unused in the kit. S130: After the operation, scan the unique serial number barcode of each used component, update the status of the corresponding component to consumed, and record the consumption timestamp; scan the unique serial number barcode of each unused component, update the status of the corresponding component to unused and recyclable, and trigger the component return process. S140: Periodically analyze all package records that have been closed in the past N days, calculate the idle rate of key components, and when the idle rate is greater than the idle threshold, generate an idle signal, mark the corresponding component as having a systemic idle risk, and obtain the corresponding inbound information. S150: Based on the warehousing information, determine whether there is a risk of inventory backlog; if so, generate a backlog warning.

[0029] Specifically, in step S110, relying on the existing surgical scheduling system and consumable management system of the hospital, at a fixed time every day (such as 16:00 in the afternoon), the surgical department nurses search and apply for the corresponding standard consumable packages in the consumable management system according to the surgical schedule of the next day, by surgical type (such as laparoscopic cholecystectomy, internal fixation of femoral fracture). The system automatically associates the basic information of the surgery and pre-fills it into the application form.

[0030] After the application is submitted, the system immediately connects to the inventory management module to retrieve the real-time inventory status of the standard consumable kit. If the inventory quantity is greater than or equal to the applied quantity and the kit is not locked or in a pending shipment state, it is determined to be in stock. The system automatically updates the inventory status of the kit from "in stock" to "planned," and simultaneously links the surgical information to the kit record. The planned surgical time is the specific time slot of the day (e.g., 9:00-11:00 AM on March 22, 2026), the surgical room is marked with the specific floor and room number (e.g., Operating Room 3 on the 5th floor of the inpatient department), and the surgeon's ID is linked to the hospital's physician information database, simultaneously retrieving auxiliary information such as the physician's name and title. For example, for a kit applied for for a laparoscopic surgery, after linking, the surgeon's ID can be clearly found to be Y001, the name is Zhang XX, the planned surgical time is 10:00 AM on March 22, and the surgical room is Operating Room 3 on the 5th floor, ensuring accurate matching between the kit and the surgery.

[0031] In step S120, the standard consumable kit is retrieved by the operating room nurse from the consumables warehouse before surgery (e.g., 4 hours prior). Upon retrieval, the warehouse administrator scans the unique identification QR code on the kit's outer packaging using a barcode scanner. This QR code is associated with the kit ID and information on all components within the kit. After scanning, the consumables management system automatically recognizes the retrieval operation, updating the kit status from "planned" to "retrieved," and simultaneously triggering the system to automatically create virtual sub-records for all components within the kit. Each virtual sub-record corresponds to a unique serial number for the component, generated at the factory and printed on the component's smallest packaging, ensuring uniqueness. By default, the system sets the initial status of all components to "in package, unused," and associates the sub-records with the kit ID and surgical information, forming a three-level association system of "kit-component-surgery." For example, a hemostatic material kit contains 10 hemostatic clips of different sizes. After receiving the kit, the system will generate 10 virtual sub-records. Each record corresponds to the serial number of a hemostatic clip, and the status of each record is "in the kit, unused". Each sub-record can be traced back to the corresponding kit and surgical information.

[0032] In step S130, after the surgery, the operating room nurse completes the verification and scanning of component usage within a set time (e.g., 30 minutes), using a dedicated barcode scanner to scan the unique serial number barcode of each component in the kit. For components already used in the surgery (e.g., suture needles, staples, etc.), after scanning, the system updates the virtual sub-record status of the component from "in package, unused" to "consumed," and automatically records the consumption timestamp to ensure the timeliness and accuracy of the consumption record. For unused components (e.g., spare sterile cotton balls, extra sutures, etc.), after scanning their serial number barcode, the system updates the status to "unused and recyclable" and immediately triggers the component return process. The system automatically generates a return application form, marking the serial number of the returned component, kit ID, surgical information, etc. After the nurse verifies that everything is correct, she organizes and packages the unused components, attaches the return application form, and the warehouse staff retrieves them. After retrieval, the warehouse administrator scans the barcode to confirm, and the system completes the return and warehousing operation, updating the component status to "recyclable and reusable."

[0033] In step S140, the system automatically performs the analysis task periodically (e.g., set to 2:00 AM daily). The N value can be flexibly configured according to the hospital's consumable management needs. It is usually set to 7 days, which means analyzing all closed kit records in the past 7 days. Closed kits refer to kits where the surgery was completed, the components were consumed, or the return process was completed.

[0034] During the analysis, the system automatically identifies key components within the kit. These key components are pre-defined by the hospital's consumables management department and are typically high-value components with fluctuating usage frequency that affect the execution of surgeries, such as special-type staplers and artificial joints. The idle rate of each key component is calculated using the formula: (Number of unused and recyclable components ÷ Total number of components issued) × 100%.

[0035] The system has preset idle thresholds, with different thresholds for different types of critical components. For example, the idle threshold for high-value components is set at 20%, and for ordinary critical components at 30%. When the idle rate of a critical component exceeds the corresponding threshold, the system automatically generates an idle signal, marking the component as having a systemic idle risk in the early warning module of the consumables management system. Simultaneously, the system retrieves the component's inventory information, including the inventory entry time, quantity, supplier, purchase price, and shelf life. For example, if a certain model of stapler was used 10 times in the past 7 days, with 3 unused and recyclable, the idle rate is 30%, exceeding the preset 20% threshold. The system generates an idle signal and retrieves the inventory information for 20 units entered on March 15th, from supplier XX Medical Company.

[0036] In step S150, after obtaining the warehousing information of key components, the system constructs an inventory backlog judgment model by combining the component's historical consumption data, current inventory quantity, and shelf life. The judgment logic is as follows: First, calculate the average monthly consumption of the component (taking the average consumption of the past 3 months), then calculate the consumption duration that the current inventory can support (current inventory quantity ÷ average monthly consumption). If the support duration exceeds the preset backlog threshold (usually set to 3 months), and the component has less than 6 months left before its expiration date, or the current inventory quantity exceeds twice the maximum monthly consumption of the past 6 months, then an inventory backlog risk is determined, and the system automatically generates a backlog warning. The warning information includes the component name, specifications, current inventory, average monthly consumption, support duration, warehousing time, and shelf life, and is pushed to the consumables procurement department and warehouse management department. For example, if a component currently has 50 units in inventory, an average monthly consumption of 10 units, and a support duration of 5 months, exceeding the 3-month threshold, and has 5 months left before its expiration date, the system determines that there is a backlog risk, generates a backlog warning, and pushes it to the relevant departments.

[0037] Reference Figure 2 Hospital consumable inventory risk warning methods also include S210-S240: S210, When receiving an emergency request for a component during operation, check whether there is available inventory of the corresponding component; S220, if yes, then generate a delivery task based on the surgical information; if no, then generate a stockout signal; S230, based on the out-of-stock signal, performs an emergency search, which includes finding alternative models, searching for in-transit inventory, transferring across hospital campuses, and contacting suppliers for emergency direct delivery; S240 integrates search results, generates an emergency decision dashboard, and pushes it to the operating room.

[0038] In addition, after the surgery in which an emergency requisition event occurs, it is also necessary to backtrack the consumption records of all packages containing emergency requisitioned components within M days; if it is found that multiple emergency requisitioned components are in the state of consumed, but other key components in the same package are in the state of unused and recyclable, then a related event record representing isolated shortage accompanied by idleness is generated.

[0039] Furthermore, it is also necessary to calculate the surgeon's habit deviation during the procedure, the first usage rate of unused recyclable components, and the second usage rate of emergency-requested components that can replace unused recyclable components; if the second usage rate is not less than k times the first usage rate and the habit deviation is below the threshold, it is marked as an abnormal consumption event.

[0040] Specifically, in step S210, the emergency requisition request during the operation is submitted through the operating room mobile nursing terminal. The nurse selects the operation number, the name, specifications, and quantity of the component to be urgently requested in the terminal. After submission, the system immediately connects to the inventory management module to retrieve the real-time available inventory of the component. The retrieval scope includes the operating room reserve inventory, the central warehouse inventory, and the reserve inventory of each clinical department. Available inventory refers to the quantity of components that are not locked, are not in the outbound process, and are within their shelf life.

[0041] After the system completes the search, if the available inventory is greater than or equal to the requested quantity, it is determined that there is available inventory; if the total available inventory within the search range is less than the requested quantity, it is determined that there is no available inventory, ensuring efficient response in emergency situations. For example, if a nurse urgently requests 5 packs of hemostatic gauze during surgery due to sudden massive bleeding, the system quickly finds 10 packs of available inventory in the central warehouse and immediately provides feedback that there is available inventory, saving time for subsequent delivery.

[0042] In step S220, if the system finds available inventory for the corresponding component, it immediately generates a delivery task based on the associated surgical information (operating room, current surgical progress). The delivery task clearly indicates the name, specifications, quantity, operating room, priority (default is "urgent"), and delivery deadline of the requested component. Simultaneously, the delivery task is pushed to the mobile terminal of the warehouse delivery personnel, who automatically receive a delivery reminder. After receiving the task, the delivery personnel confirm the order in the system and begin the delivery process. If the system finds no available inventory, it immediately generates a stockout signal. The stockout signal includes the component name, specifications, requested quantity, surgical information, and stockout type (completely out of stock / partially out of stock).

[0043] In step S230, after the system generates a shortage signal, it triggers an emergency search process. The emergency search consists of four parallel stages: First, finding alternative models. Based on the functional attributes and specifications of the shortage component, the system filters out components from the consumables substitution list that can be fully or partially replaced. The substitution list is prepared in advance by the hospital's medical equipment department in conjunction with clinical departments, clearly defining the substitution relationships between different components. For example, if a certain model of suture is out of stock, the system filters out another model of suture with similar functions and compatible specifications as a substitute. Second, searching for in-transit inventory. The system connects to the procurement and logistics system to retrieve in-transit orders for the shortage component, querying logistics progress and estimated delivery time. If the in-transit inventory is expected to arrive within one hour... If delivery is possible, priority will be given to waiting for goods already in transit; thirdly, for inter-hospital transfers, if the hospital has multiple campuses, the system will automatically search for available inventory of the component in other campuses, generate an inter-hospital transfer request, and push it to the warehouse management department of the corresponding campus. The request should specify the transfer quantity, receiving campus, and receiving department. Once the recipient confirms, the transfer process will be initiated; fourthly, for emergency direct delivery to suppliers, the system will automatically retrieve the emergency contact information (telephone, WeChat) of the corresponding supplier for the component, and generate an emergency direct delivery request form, which will be sent to the supplier, specifying the component name, specifications, quantity, delivery address (operating room), and delivery time limit. A dedicated person will be assigned to follow up on the supplier's response to ensure the comprehensiveness and efficiency of the emergency search.

[0044] In step S240, after completing the emergency search, the system automatically integrates the search results from the four stages to generate a standardized emergency decision dashboard. The dashboard uses a visual format to clearly present the results of each search stage, including the availability, specifications, and inventory quantity of alternative models; the logistics progress and estimated delivery time of inventory in transit; the available quantity and time required for inter-hospital transfers; and the response status and estimated delivery time of emergency direct delivery from suppliers. It also indicates the priority of each option (e.g., if an alternative model is in stock, it is marked as the "preferred option"). After the dashboard is generated, it is pushed to the operating room display screen in real time through the hospital's internal system, allowing the surgeon to select the appropriate emergency plan based on the urgency of the surgery. For example, if the emergency decision dashboard shows "5 packs of alternative model A are in stock and can be delivered immediately, estimated delivery in 20 minutes; inventory in transit is estimated to arrive in 1.5 hours," the surgeon can select alternative model A to ensure the smooth progress of the surgery.

[0045] After a surgery involving an emergency requisition (e.g., within one hour of surgery), the system automatically triggers a retrospective analysis process. The M value can be set according to the hospital's needs, but is typically set to 3 days. This means the system retrospectively analyzes the consumption records of all kits containing that emergency requisitioned component within the past 3 days. The system filters relevant kits by component name and specifications, extracts consumption details for each kit, including kit ID, surgery information, quantity of components consumed, unused and recyclable quantity, and consumption time. All relevant records are integrated into a retrospective report to facilitate subsequent analysis of the reasons for the emergency requisition and to determine if any anomalies exist. For example, if a hemostatic clip was urgently requisitioned during a surgery, after the surgery, the system retrospectively analyzes all kits containing that model of hemostatic clip within the past 3 days, extracts their consumption records, and checks for similar emergency requisitions.

[0046] During the retrospective analysis, the system compares the consumption status of components within each relevant kit. If it finds three or more cases (the threshold can be adjusted based on the hospital's actual situation) where urgently requested components are "consumed," but other key components within the same kit (related to the function of the urgently requested components or essential surgical components) are "unused and recyclable," it is determined that there is an isolated shortage accompanied by idleness. The system automatically generates a related event record representing this situation. The record includes the kit ID, surgical information, the name, quantity, and consumption status of the urgently requested components, as well as the name, quantity, and status of the unused and recyclable key components within the same kit. It also indicates the occurrence time of the related event and the attending surgeon involved. For example, if an urgently requested hemostatic clip in a kit has been consumed, but the hemostatic gauze in the same kit is unused and recyclable, and four similar cases have occurred in the past three days, the system generates a related event record, noting the relevant details.

[0047] Simultaneously, the system calculates three key indicators: First, the surgeon's habit deviation rate for this surgery. This is calculated by first extracting the average consumption rate of relevant components in the kit (e.g., the average consumption rate of hemostatic clips is 80%) in similar surgeries performed by the surgeon in the past 6 months, and then calculating the actual consumption rate of the component in this surgery. The absolute value of the difference between the two is the habit deviation rate. The lower the deviation rate, the more stable the surgeon's surgical habits. Second, the first utilization rate of unused recyclable components. This is calculated by the average utilization rate of unused recyclable components in similar surgeries performed in the past 6 months, reflecting the regular usage needs of the components. Third, the second utilization rate of emergency-requisitioned components that can replace unused recyclable components. This is calculated by the average utilization rate of emergency-requisitioned components in similar surgeries performed in the past 6 months, reflecting the actual demand for the components. For example, in the past 6 months, the average consumption rate of hemostatic gauze in similar surgeries by a certain surgeon was 70%, while the actual consumption rate in this surgery was 30%, with a deviation from the usual practice of 40%; the first use rate of hemostatic gauze was 65%, and the second use rate of emergency-requested alternative hemostatic materials was 75%.

[0048] The system compares the calculated second usage rate, first usage rate, and habit deviation with preset thresholds. The k-value is typically set to 2 (which can be adjusted based on the hospital's actual situation), and the habit deviation threshold is typically set to 15% (i.e., a deviation below 15% is considered a stable surgical habit for the physician). If the second usage rate is not less than k times the first usage rate (i.e., second usage rate ≥ 2 × first usage rate), and the habit deviation is below 15%, then the emergency requisition event is determined to be not caused by fluctuations in the physician's surgical habits, but rather by abnormal consumption. The system automatically marks this event as an abnormal consumption event, records relevant indicators and event details, and pushes the information to the consumables management department and clinical departments. For example, if the second usage rate of an emergency requisition component is 80%, the first usage rate is 35%, 80% ≥ 2 × 35%, and the physician's habit deviation is 10%, which is below 15%, the system marks it as an abnormal consumption event. If the deviation from the standard operating procedure (SOP) is ≥15%, the emergency requisition event is determined to be caused by fluctuations in the surgeon's surgical habits. This situation is not considered abnormal consumption, and the system will not mark it as abnormal. Instead, the event will be recorded and archived in the "Surgeon's Habit Fluctuation Record" database. A notification will also be sent to the corresponding surgeon and the head nurse of the department, reminding them to pay attention to fluctuations in surgical habits and suggesting adjustments based on recent surgical cases to avoid frequent emergency requisitions in the future. If the second usage rate is <2 × the first usage rate, regardless of whether the deviation from the standard operating procedure is below the threshold, it is determined to be a normal fluctuation in clinical demand (such as temporary consumable needs caused by differences in patient conditions or changes in surgical complexity). The system will not mark this as abnormal and will archive the emergency requisition event as a regular consumption record.

[0049] Reference Figure 3 Hospital consumable inventory risk warning methods also include S310-S340: S310, after generating a record of associated events representing isolated shortages accompanied by idleness or after marking an abnormal consumption event, retrieve the clinical event calendar within 24 hours before and after the abnormal signal event point. S320, determine whether there are preset high-risk clinical event labels in the clinical event calendar. High-risk clinical event labels include intraoperative complications, temporary changes in surgical procedures, and emergency surgery intervention. S330, if so, mark the associated event record or abnormal consumption event as a clinically reasonable variant and remove the corresponding risk warning; S340, if not, then confirm the management anomaly and trigger configuration optimization suggestions for the corresponding component or package.

[0050] Specifically, in step S310, after generating a record of associated events representing isolated shortages accompanied by idleness, or after marking an abnormal consumption event, the system immediately retrieves the clinical event calendar within 24 hours before and after the abnormal signal event point. The clinical event calendar is jointly provided by the hospital's surgical anesthesia system, emergency system, and nursing system, and includes all surgery-related clinical events, such as intraoperative complications, changes in surgical procedures, emergency surgical intervention, and changes in the patient's condition.

[0051] In step S320, after retrieving the clinical event calendar, the system compares it with preset high-risk clinical event tags. These tags are pre-defined and entered into the system by the hospital's medical quality management department, and explicitly include three categories: intraoperative complications (such as massive bleeding, organ damage, infection, etc.), temporary changes in surgical procedures (such as changing laparoscopic surgery to open surgery, or routine surgery to emergency surgery, etc.), and emergency surgery intervention (i.e., emergency surgery inserted temporarily, resulting in adjustments to the original surgical plan). The system uses keyword matching and event type comparison to determine whether any of the above three types of tags exist in the clinical event calendar. If they exist, the abnormal signal is determined to be related to clinical factors; if they do not exist, the abnormal signal is determined to be unrelated to clinical factors and may be caused by management issues.

[0052] In step S330, if the system determines that a preset high-risk clinical event label exists in the clinical event calendar, it indicates that the associated event record or abnormal consumption event is caused by a sudden clinical situation, which is a reasonable clinical fluctuation and not a management anomaly. The system marks the associated event record or abnormal consumption event as a clinically reasonable variant, removes the corresponding risk warning, deletes the warning label from the system, and archives the relevant record to the clinically reasonable event database. For example, if a sudden massive hemorrhage occurs during surgery (intraoperative complication), and hemostatic materials are urgently requested, resulting in other components in the same kit not being used, the system marks this as a clinically reasonable variant and removes the idle or abnormal consumption warning.

[0053] In step S340, if the system determines that there is no preset high-risk clinical event label in the clinical event calendar, it means that the associated event record or abnormal consumption event is not caused by clinical factors, but by problems such as unreasonable consumable configuration and non-standard management. The system confirms that there is a management abnormality and triggers the configuration optimization suggestion process for the corresponding component or package.

[0054] Reference Figure 4 and Figure 5 The specific steps that trigger configuration optimization recommendations for this component or suite include S410-S430 and S410, S510-S540: S410 identifies the type of abnormal signal; S420, if it is to characterize the associated event of isolated shortage accompanied by idleness, then the component consumption matrix of the standard consumable package within the preset period is statistically analyzed, and the emergency requisition frequency of the shortage component and the unused rate of the idle component are calculated. S430 generates incremental configuration suggestions for shortage components based on the frequency of emergency applications, and generates suggestions for reducing or eliminating idle components based on the unused rate, and merges them to generate a package structure reorganization plan. S510, If it is an abnormal consumption event, extract the components urgently requested during the operation as the preferred components, and lock the original components in the same package that are unused, recyclable and have similar functional attributes to the preferred components. S520: Obtain the surgeon's historical surgical preference data based on the surgeon's ID, and construct a personalized demand model for the surgeon. The model is used to represent the surgeon's preference weight vector for different specification attribute components. S530: Input the attribute features of the preferred components into the physician's personalized needs model to obtain the preference fit for the corresponding surgeon. S540, if the preference fit is greater than the preset fit threshold, it is determined that the preferred component matches the long-term preference characteristics of the corresponding surgeon, and a special package configuration suggestion is generated for the surgeon, replacing the original component with the preferred component.

[0055] Specifically, in step S410, after the system triggers the configuration optimization suggestion process, it first identifies the type of abnormal signal. By retrieving the tagging information of the abnormal event, it distinguishes whether the abnormal signal represents an isolated shortage accompanied by idleness or an abnormal consumption event. During the identification process, the system extracts the core features of the abnormal event, such as keywords like "isolated shortage" and "idle component" for associated events, and keywords like "abnormal consumption" and "physician preference" for abnormal consumption events. At the same time, it combines the indicator data in the event record (such as idle rate, usage rate, and habit deviation) to ensure the accuracy of type identification.

[0056] In step S420, if an abnormal signal is identified as a related event characterized by isolated shortages accompanied by idleness, the system calculates a component consumption matrix for the standard consumable kit within a preset period (usually set to 1 month). The consumption matrix is ​​presented in tabular form, including data such as the name, specifications, quantity issued, quantity consumed, unused recyclable quantity, and frequency of emergency requisitions for each component in the kit, clearly showing the consumption status of each component. Simultaneously, the system calculates the frequency of emergency requisitions for shortage components (i.e., the total number of emergency requisitions for that component within the preset period) and the unused rate of idle components (unused recyclable quantity ÷ issued quantity × 100%). For example, if a kit is issued 10 times within 1 month, with component A being urgently requisitioned 3 times and component B having 5 unused recyclable units and 10 issued, the unused rate is 50%.

[0057] In step S430, the system generates incremental configuration suggestions for shortage components based on the frequency of emergency requests and the average monthly consumption of those components. For example, if a shortage component is requested an average of 5 times per month, with an average of 2 units requested each time, the system suggests increasing the number of these components in the package from 3 to 5, while also increasing the reserve inventory in the central warehouse to ensure that surgical needs are met. Based on the unused rate of idle components, the system generates suggestions for reducing or removing idle components. If the unused rate of an idle component exceeds 40% and there are no emergency requests in the past 3 months, the system suggests halving the number of these components in the package. If the unused rate exceeds 60%, the system suggests removing the component from the package to avoid resource waste. Finally, the system merges the incremental configuration suggestions and the reduction / removal suggestions to generate a complete package restructuring plan, which clearly defines the adjusted component list, configuration quantity, reasons for adjustment, and implementation timeline.

[0058] In step S510, if an abnormal signal is identified as an abnormal consumption event, the system automatically extracts the urgently requested component from the surgery as the preferred component, recording its name, specifications, functional attributes, and usage scenario. Simultaneously, it locks the original component within the same kit that is in a "unused and recyclable" state and has similar functional attributes to the preferred component—that is, the component configured in the original kit that can be replaced by the preferred component. During the locking process, the system compares the component's functional description, specifications, and applicable surgical types to ensure that the original component and the preferred component have similar functions and are interchangeable. For example, if an urgently requested type A suture (fine needle, absorbable) is selected as the preferred component, the system locks the unused and recyclable type B suture (fine needle, absorbable) within the same kit; both have identical functional attributes and are interchangeable.

[0059] In step S520, the system extracts all similar surgical records from the hospital's physician information database and surgical consumption database within the past 6 months based on the surgeon's ID. It then filters out consumption data involving the preferred component and the original component, including usage frequency, quantity, and substitution status, to construct a personalized physician needs model. This model can employ machine learning algorithms, using the physician's surgical type, surgical difficulty, and patient condition as input variables, and the physician's usage frequency percentage for different specification attributes as the output variable. This generates a weight vector representing the physician's preference for different specification attributes; a higher weight vector value indicates a higher degree of preference for that component. For example, if a surgeon used type A sutures 85% of the time and type B sutures 15% of the time in the past 6 months, the preference weight for type A would be 0.85, and for type B, 0.15.

[0060] In step S530, the system organizes the attribute characteristics (such as specifications, materials, functions, and applicable scenarios) of the preferred components into standardized feature vectors, which are then input into the constructed physician personalized needs model. The model calculates the matching degree between the feature vectors and the physician's preference weight vector to obtain the preference fit for the surgeon. The fit value ranges from 0 to 1. The higher the fit, the more the preferred component matches the surgeon's surgical habits and needs. For example, the attribute characteristics of preferred component A have a high matching degree with the physician's preference weight vector, resulting in a fit value of 0.88, indicating that the component is very much in line with the physician's preferences.

[0061] In step S540, the system presets an adaptation threshold, typically set to 0.8 (which can be adjusted based on the hospital's actual situation). If the calculated preference adaptation degree is greater than this preset threshold, the preferred component is determined to match the long-term preference characteristics of the corresponding surgeon. The system then generates a customized kit configuration suggestion for that surgeon. The suggestion explicitly replaces the original components in the kit that have similar functions to the preferred component with the preferred component, and adjusts the configuration quantity of that component in the kit to match the surgeon's usage habits. For example, if a surgeon's adaptation degree for preferred component A is 0.88, which is greater than the threshold of 0.8, the system suggests replacing the original type B sutures with type A sutures in the surgeon's customized kit, and increasing the configuration quantity from 3 to 4, to ensure that it matches the surgeon's preferences and reduce emergency requests and idle situations.

[0062] Reference Figure 6 The hospital consumables inventory risk warning also includes S610-S640: S610, after generating package configuration optimization suggestions, distinguishes the component attribute types, including common components and personalized components; S620, for common components, aggregates historical consumption data of all physicians in the hospital to generate a hospital-wide total volume forecast purchase order; S630, for personalized components, scans the surgical schedule within the future preset period, extracts the planned number of surgeries for a specific surgeon, and calculates the expected demand by combining the historical consumption rate of the target component for the specific surgeon. S640 generates a purchase requisition form with a physician-reserved label based on the expected demand.

[0063] Specifically, in step S610, after generating package configuration optimization suggestions, the system distinguishes the attribute types of components. The criteria for classifying attribute types are pre-defined and entered into the system by the hospital's consumables management department. Common components refer to components that can be used by all clinical departments and surgeons throughout the hospital, with universal functions, uniform specifications, and no obvious personalized requirements, such as ordinary sutures, sterile cotton balls, and disposable gloves. Personalized components refer to components with special specifications and functional requirements for specific surgeons and specific surgical types, applicable only to specific scenarios, such as special-model staplers for a particular surgeon or special consumables for rare surgeries. The system distinguishes attribute types and generates lists of common and personalized components based on information such as component name, specifications, scope of use, and physician preference records.

[0064] In step S620, for common components, the system aggregates historical consumption data from all physicians across the hospital over the past three months, including the average monthly consumption quantity, consumption fluctuation range, and seasonal variations (such as increased consumption of certain consumables during peak surgical periods). Combined with factors such as the hospital's total surgical schedule for the next month and the number of clinical department beds, a trend prediction algorithm is used to predict the total demand for common components across the hospital for the next month. Based on this, a 10%-15% reserve is added, generating a hospital-wide total quantity forecast purchase order. The purchase order clearly specifies the component name, specifications, forecast demand, reserve quantity, unit price, estimated purchase amount, and supplier recommendations, and is pushed to the consumables procurement department. For example, if the hospital's average monthly consumption of ordinary sutures is 5000 packs, and the forecast for the next month is 5200 packs, a 10% reserve is added, generating a purchase order for 5720 packs.

[0065] In step S630, for personalized components, the system first scans the hospital's surgical schedule for the next preset period (usually set to 1 month). It then filters the planned number of surgeries for a specific surgeon by surgeon ID and extracts the historical usage rate (i.e., the average number of times the component is used per similar surgery) of the corresponding personalized component from the surgical consumption database. For example, if a surgeon plans to perform 12 joint replacement surgeries in the next month, the historical usage rate of their dedicated artificial joint is 1 per surgery. The system combines these two data points to calculate the expected demand for the personalized component (expected demand = planned number of surgeries × historical usage rate). Considering emergencies, a 5%-10% reserve is added to ensure the physician's personalized needs are met. For example, if the expected demand for the aforementioned artificial joint is 12, adding a 5% reserve results in a final expected demand of 12.6, rounded down to 13.

[0066] In step S640, the system generates a purchase requisition form with a physician-reserved tag based on the expected demand for personalized components. The requisition form clearly indicates the component name, specifications, expected demand, spare quantity, corresponding surgeon's ID and name, reservation identifier (marked "Physician-Specific Reservation"), purchase deadline, and supplier information. This ensures that the purchased personalized components are accurately allocated to the corresponding surgeons, avoiding allocation confusion or idleness. After the purchase requisition form is generated, it is pushed to the consumables procurement department, which purchases according to the requisition. Upon receipt, the system marks the component with the corresponding physician's reservation tag. When distributing, the warehouse management department prioritizes issuing components with reservation tags to the corresponding physicians.

[0067] Based on the above method embodiments, the second embodiment of this application discloses a hospital consumables inventory risk early warning system. The hospital consumables inventory risk early warning system of this application embodiment can implement any of the above-described hospital consumables inventory risk early warning methods, and the specific working process of each module in the hospital consumables inventory risk early warning system can be referred to the corresponding process in the above method embodiments.

[0068] For ease of understanding, an example is as follows: A hospital consumables inventory risk early warning system includes: The consumables requisition module is used to requisition the corresponding standard packages of consumables based on the surgical schedule for the next day. The status processing module is used to update the status to "planned" when it is confirmed that the standard consumable kit is in stock, and to associate it with surgical information, including the planned surgical time, operating room, and surgeon ID. It is also used to update the status to "received" after the standard consumable kit is physically retrieved, and to create virtual sub-records for all components in the standard consumable kit. The initial status of each component is set to "in package, unused". The scanning module is used to scan the unique serial number barcode of each used component and the unique serial number barcode of each unused component after the operation; the status processing module updates the status of the corresponding component to consumed and records the consumption timestamp, and updates the status of the corresponding component to unused and recyclable, and triggers the component return process. The package record analysis module is used to periodically analyze all package records that have been closed in the past N days, calculate the idle rate of key components, generate an idle signal when the idle rate is greater than the idle threshold, mark the corresponding component as having a systemic idle risk, obtain the corresponding inbound information, and also use the inbound information to determine whether there is an inventory backlog risk; if so, a backlog warning is generated.

[0069] The third embodiment of this application provides a computer device, which may include a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement a hospital consumables inventory risk warning method.

[0070] The memory can communicate with the processor via a communication bus, which can be an address bus, a data bus, a control bus, etc.

[0071] Additionally, the memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0072] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0073] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a method for early warning of hospital consumable inventory risks.

[0074] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0075] It should be noted that the computer device and storage medium in this application embodiment are respectively electronic devices and storage media for applying the above-described hospital consumables inventory risk warning method. Therefore, all embodiments of the above-described hospital consumables inventory risk warning method are applicable to the computer device and storage medium, and can achieve the same or similar beneficial effects. For the computer device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the descriptions of the method embodiments.

[0076] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0077] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for early warning of inventory risks in hospital consumables, characterized in that, include: According to the surgery schedule for the next day, the corresponding standard package of consumables is requested, and when it is confirmed that the standard package of consumables is in stock, the status is updated to "planned" and associated with the surgery information, including the planned surgery time, operating room, and surgeon ID; After the standard consumable kit is physically claimed, the status is updated to claimed, and a virtual sub-record is created for all components within the standard consumable kit. The initial status of each component is set to unused in the kit. After the operation, scan the unique serial number barcode of each used component, update the status of the corresponding component to consumed, and record the consumption timestamp; scan the unique serial number barcode of each unused component, update the status of the corresponding component to unused and recyclable, and trigger the component return process; Regularly analyze all package records that have been closed in the past N days, calculate the idle rate of key components, and when the idle rate is greater than the idle threshold, generate an idle signal, mark the corresponding component as having a systemic idle risk, and obtain the corresponding inbound information; Based on the warehousing information, determine whether there is a risk of inventory backlog; if so, generate a backlog warning.

2. The method for early warning of hospital consumable inventory risk according to claim 1, characterized in that, The hospital consumables inventory risk early warning method also includes: When an emergency request for a component is received during operation, check if there is available inventory of the corresponding component; If yes, a delivery task is generated based on the surgical information; otherwise, a stockout signal is generated. Based on the out-of-stock signal, an emergency search is performed, which includes finding alternative models, searching for in-transit inventory, transferring across hospital campuses, and contacting suppliers for emergency direct delivery. The search results are integrated to generate an emergency decision dashboard, which is then pushed to the operating room.

3. The method for early warning of hospital consumable inventory risk according to claim 2, characterized in that, The hospital consumables inventory risk early warning method also includes: After the surgery that resulted in an emergency claim event, backtrack all package consumption records containing emergency claim components within M days. If multiple instances of urgently requested components are found to be in the state of consumed, but other critical components within the same package are in the state of unused and recyclable, then a related event record representing isolated shortages accompanied by idleness is generated.

4. The method for early warning of hospital consumable inventory risk according to claim 3, characterized in that, The hospital consumables inventory risk early warning method also includes: After the surgery in which an emergency requisition event occurs, the surgeon's deviation from the usual practice for this surgery, the first usage rate of the unused recyclable component, and the second usage rate of the emergency requisition component that can replace the unused recyclable component are calculated. If the second usage rate is not less than k times the first usage rate and the habit deviation is below the threshold, it is marked as an abnormal consumption event.

5. The method for early warning of hospital consumable inventory risk according to claim 4, characterized in that, The hospital consumables inventory risk early warning method also includes: After generating a record of associated events characterized by isolated shortages accompanied by idleness, or after being marked as abnormal consumption events, retrieve the clinical event calendar within 24 hours before and after the abnormal signal event point; Determine whether there are preset high-risk clinical event tags in the clinical event calendar. The high-risk clinical event tags include intraoperative complications, temporary changes in surgical procedures, and emergency surgical intervention. If yes, mark the associated event record or the abnormal consumption event as a clinically reasonable variant and remove the corresponding risk warning; if no, confirm the management abnormality and trigger configuration optimization suggestions for the corresponding component or package.

6. The method for early warning of hospital consumable inventory risk according to claim 5, characterized in that, The specific steps for triggering configuration optimization suggestions for this component or suite include: Identify the type of abnormal signal; If the event is to characterize the associated event of isolated shortage accompanied by idleness, then the component consumption matrix of the standard package of consumables is statistically analyzed within a preset period, and the frequency of emergency requisition of shortage components and the unused rate of idle components are calculated. Based on the frequency of emergency applications, incremental configuration suggestions for the shortage components are generated, and suggestions for reducing or eliminating the idle components are generated based on the unused rate. These suggestions are then combined to generate a package structure reorganization scheme. If it is an abnormal consumption event, the components urgently requested during the operation are extracted as preferred components, and the original components in the same package that are unused, recyclable, and have similar functional attributes to the preferred components are locked. Based on the surgeon's ID, their historical surgical preference data is obtained, and a personalized demand model for the physician is constructed. The personalized demand model for the physician is used to represent the physician's preference weight vector for different specification attribute components. The attribute features of the preferred components are input into the physician's personalized needs model to obtain the preference fit for the corresponding surgeon. If the preference fit is greater than the preset fit threshold, it is determined that the preferred component matches the long-term preference characteristics of the corresponding surgeon, and a customized package configuration suggestion is generated for the surgeon, replacing the original component with the preferred component.

7. A method for early warning of hospital consumable inventory risk according to claim 5, characterized in that, The hospital consumables inventory risk warning also includes: After generating package configuration optimization suggestions, the component attribute types are distinguished, including common components and personalized components; For the aforementioned common components, historical consumption data of all physicians in the hospital are aggregated to generate a hospital-wide total volume forecast procurement order; For the personalized component, the surgical schedule within the future preset period is scanned, the planned number of surgeries for a specific surgeon is extracted, and the expected demand is calculated by combining the historical consumption rate of the target component corresponding to the specific surgeon. A purchase requisition form with a physician-reserved label is generated based on the expected demand.

8. A hospital consumables inventory risk early warning system, characterized in that, The method for early warning of hospital consumable inventory risk as described in any one of claims 1 to 7 includes: The consumables requisition module is used to requisition the corresponding standard packages of consumables based on the surgical schedule for the next day. The status processing module is used to update the status to "planned" when it is confirmed that the standard consumable kit is in stock, and associate it with surgical information, including the planned surgical time, operating room, and surgeon ID. It is also used to update the status to "received" after the standard consumable kit is physically retrieved, and to create a virtual sub-record for all components in the standard consumable kit. The initial status of each component is set to "in package, unused". The scanning module is used to scan the unique serial number barcode of each used component and the unique serial number barcode of each unused component after the operation; the status processing module updates the status of the corresponding component to consumed and records the consumption timestamp, and updates the status of the corresponding component to unused and recyclable, and triggers the component return process; The package record analysis module is used to periodically analyze all package records that have been closed in the past N days, calculate the idle rate of key components, generate an idle signal when the idle rate is greater than the idle threshold, mark the corresponding component as having a systemic idle risk, obtain the corresponding inbound information, and also use the inbound information to determine whether there is an inventory backlog risk; if so, generate a backlog warning.

9. A computer device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the hospital consumables inventory risk warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images