Disinfection supply center workflow optimization system based on big data analysis

Abstract

The invention discloses a disinfection supply center workflow optimization system based on big data analysis, particularly relates to the technical field of medical data processing, and is used for solving the problems of resource squeezing and delayed timeliness caused by insufficient dynamic demand adaptation in existing disinfection task scheduling. By integrating instrument demand time sequence distribution, infection risk levels and equipment space distribution data, dynamically evaluating instrument reuse priorities, marking department cooperation nodes, tracking pollution risks of a storage area in real time and dynamically correcting a disinfection resource scheduling path based on multi-dimensional decision parameters, real-time balanced adaptation of task priorities and equipment loads is achieved; according to the composite weight autonomous generation optimization scheme of the pollution diffusion rate, the department cooperation frequency and the equipment transportation efficiency, the dispatching timeliness of the key instruments and the environmental safety of the storage area are synchronously guaranteed in the sudden high-load scene, and the emergency response capability and the resource utilization efficiency of the disinfection supply center are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and more specifically, to a disinfection supply center workflow optimization system based on big data analysis. Background Art

[0002] When a disinfection supply center faces sudden disinfection tasks, the equipment demands of multiple departments often result in scheduling conflicts due to overlapping time windows or limited equipment resources. Existing methods are usually based on preset rules, such as allocating disinfection resources according to department priority or task urgency, which makes it difficult to adapt to dynamic demand changes in real time. For example, when multiple departments submit emergency tasks at the same time, delays in scheduling of key equipment or equipment idling are likely to occur, affecting the efficiency of emergency response.

[0003] The existing disinfection task scheduling method lacks a dynamic coordination mechanism when dealing with the concurrent needs of multiple departments, and it is difficult to balance the multiple goals of resource allocation. Especially in sudden high-load scenarios, fixed rules can easily lead to local resource squeezes or task priority misalignment, affecting the timeliness and safety of medical work. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a disinfection supply center workflow optimization system based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A disinfection supply center workflow optimization system based on big data analysis, including:

[0007] Multi-source acquisition module: obtain multi-source real-time information from the disinfection supply center, including future equipment use needs, equipment infection risk level, equipment collaborative use information and disinfection equipment spatial distribution map;

[0008] Urgency analysis module: Determine the urgency of device reuse based on the temporal distribution of future device usage needs and the device infection risk level;

[0009] Collaboration analysis module: Determine the degree of departmental collaboration based on the collaborative use information of equipment, and mark the department nodes in the current conflicting tasks;

[0010] Dynamic sorting module: When the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; otherwise, the conflicting tasks are sorted hierarchically based on the closeness of departmental collaboration;

[0011] Environmental monitoring module: monitors the air cleanliness of the storage area of ​​sterilized instruments. If the air cleanliness exceeds the preset cleanliness threshold and indicates the risk of secondary contamination, it triggers a re-evaluation of the priority of conflicting tasks.

[0012] Resource allocation module: based on the priority re-evaluation results and the spatial distribution map of disinfection equipment, it updates the spatiotemporal resource conflict path and dynamically allocates disinfection resources.

[0013] In a preferred embodiment, obtaining multi-source real-time information of the disinfection supply center includes:

[0014] Obtain the instrument disinfection request data submitted by each department, which includes instrument type, quantity and expected disinfection completion time;

[0015] Extract future surgery scheduling data from the hospital information management system and analyze future equipment usage requirements in the surgery scheduling data;

[0016] Retrieve the preset association table between device type and infection risk level to determine the device infection risk level of the currently disinfected device;

[0017] Count the frequency of collaborative use of instruments in historical department joint surgery records and generate information on collaborative use of instruments between departments;

[0018] Collect the real-time location coordinates and transportation route topology data of disinfection equipment to build a spatial distribution map of disinfection equipment.

[0019] In a preferred embodiment, the urgency of device reuse is determined based on the temporal distribution of future device usage requirements and the device infection risk level, including:

[0020] Divide the temporal distribution of future equipment usage demand into multiple continuous time periods according to preset time slices, and count the total demand for each equipment type in each time period;

[0021] Set the risk weighting coefficient for each device type according to the device infection risk level;

[0022] Multiply the total demand of each device type in the same period by its corresponding risk weighting coefficient to obtain the weighted demand value of each device type;

[0023] The weighted demand values ​​of the same device type in all time periods are accumulated to generate a cumulative urgency score for the corresponding device type to evaluate the urgency of device reuse.

[0024] In a preferred embodiment, the risk weighting coefficients of each device type are set as follows: a high risk level corresponds to a first weighting coefficient, a medium risk level corresponds to a second weighting coefficient, and a low risk level corresponds to a third weighting coefficient.

[0025] In a preferred embodiment, determining the degree of department collaboration based on the equipment collaborative use information and marking the department nodes in the current conflicting tasks includes:

[0026] Extract collaborative events of the same instrument type from historical department joint surgery records, and count the number of consecutive triggering of collaborative events for each pair of department combinations within the preset time window;

[0027] The coordination time sensitivity parameter is set according to the time interval distribution law of coordination events, and coordination events with continuous triggering intervals less than a preset threshold are marked with high sensitivity;

[0028] Identify department combinations with high-sensitivity markers and generate department collaboration levels by sorting them according to the number of consecutive triggering of collaborative events;

[0029] Analyze the historical collaboration closeness levels of the equipment application departments in the current conflicting task. If there are several combinations ranked in the top closeness levels in the corresponding related departments, mark them as key collaboration nodes.

[0030] The resource allocation path of conflicting tasks is dynamically adjusted according to the difference in the closeness levels of key collaborative nodes, giving priority to meeting the equipment reuse needs of high-closeness level combinations.

[0031] In a preferred embodiment, when the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; otherwise, the conflicting tasks are hierarchically sorted based on the closeness of department collaboration, including:

[0032] Compare the cumulative urgency score with the dynamic urgency threshold, which is set based on the average daily demand for the same type of device during the same period in history;

[0033] When the cumulative urgency score exceeds the dynamic urgency threshold, the sterilization priority of the associated conflicting tasks is marked as the highest level and the dedicated sterilization equipment resources are locked;

[0034] When the cumulative urgency score does not exceed the dynamic urgency threshold, the collaboration level of the equipment application departments in the conflicting tasks is extracted, and the task sequence is generated in descending order of the level ranking;

[0035] Calculate the collaboration density level difference of adjacent tasks in the task sequence. If the collaboration density level difference exceeds the preset split threshold, split them into independent processing groups.

[0036] The sterilization batches are merged based on the compatibility of the sterilization parameters of the instruments in the independent processing groups. The tasks in the same batch share the sterilization equipment and execute the transportation instructions synchronously.

[0037] In a preferred embodiment, the air cleanliness of the sterilized instrument storage area is monitored. If the air cleanliness exceeds a preset cleanliness threshold and indicates a secondary contamination risk, a priority reassessment of conflicting tasks is triggered, including:

[0038] Obtain air cleanliness monitoring data of the storage area of ​​sterilized instruments, including suspended particle concentration and microbial colony count;

[0039] If any of the suspended particle concentration and microbial colony count exceeds the upper limit of the threshold range, it will be marked as a secondary pollution risk event;

[0040] The pollution risk diffusion rate is calculated based on the duration of the secondary pollution risk event. The pollution risk diffusion rate is the growth of the pollution index per unit time.

[0041] Extract the task list involving the risk storage area in the current conflicting task queue, and generate a reassessment task sequence from high to low according to the pollution risk diffusion rate.

[0042] In a preferred embodiment, according to the priority re-evaluation results and the spatial distribution map of the disinfection equipment, the spatiotemporal resource conflict path is updated and the disinfection resources are dynamically allocated, including:

[0043] Extract the re-evaluation task sequence in the priority re-evaluation result and the real-time location coordinates of the equipment in the spatial distribution map of the disinfection equipment;

[0044] Calculate the shortest transportation time from each device to the target area based on the real-time location coordinates of the device and the path topology data of the task-related storage area;

[0045] Generate an emergency task group according to the order of the re-evaluated task sequence, and mark the equipment with the shortest transportation time less than the preset response threshold as available resources;

[0046] Adjust device allocation priority based on the dynamic load factor of available resources. The dynamic load factor is the ratio of the remaining time in the device's current task queue to the maximum load time.

[0047] Merge the tasks with compatible sterilization parameters in the emergency task group into the same batch, and execute the batch tasks in descending order of equipment allocation priority.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. By building a multi-dimensional real-time decision-making system, the urgency of equipment reuse, the closeness of departmental collaboration and dynamic environmental risk monitoring are deeply coupled to form a scheduling closed loop with self-feedback capabilities; based on the resource conflict characteristics of dynamic evolution in time and space, an optimized path that takes into account sterilization efficiency, equipment load balancing and infection prevention and control is automatically generated; when a department suddenly needs a high-infection risk device, the current equipment transportation timeliness, the frequency of collaboration with adjacent departments and the trend of pollution spread in the storage area are simultaneously calculated, and a multi-objective collaborative emergency allocation strategy is automatically triggered. The cross-domain data real-time interaction and dynamic weight allocation mechanism solve the separation of resource scheduling and risk prevention and control in traditional methods.

[0050] 2. By introducing a priority re-evaluation mechanism driven by environmental cleanliness, it is possible to capture in real time the potential threat of abnormal air pollution indicators to equipment safety, and dynamically associate the pollution diffusion rate with the equipment scheduling path, to achieve delay-free linkage between risk warning and resource scheduling; when it is monitored that the concentration of suspended particles in a storage area has increased abnormally, not only will the backlog of tasks in this area be given priority, but the task allocation logic of equipment in the surrounding areas will also be actively adjusted according to the pollution propagation model. The dynamic strategy iteration based on environmental situation awareness builds a three-dimensional safety line of defense while ensuring the timeliness of disinfection. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a structural schematic diagram of a disinfection supply center workflow optimization system based on big data analysis according to the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Example: Figure 1 A structural schematic diagram of a disinfection supply center workflow optimization system based on big data analysis of the present invention is given, and a disinfection supply center workflow optimization system based on big data analysis includes:

[0054] Multi-source acquisition module: obtain multi-source real-time information from the disinfection supply center, including future equipment use needs, equipment infection risk level, equipment collaborative use information and disinfection equipment spatial distribution map;

[0055] Urgency analysis module: Determine the urgency of device reuse based on the temporal distribution of future device usage needs and the device infection risk level;

[0056] Collaboration analysis module: Determine the degree of departmental collaboration based on the collaborative use information of equipment, and mark the department nodes in the current conflicting tasks;

[0057] Dynamic sorting module: When the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; otherwise, the conflicting tasks are sorted hierarchically based on the closeness of departmental collaboration;

[0058] Environmental monitoring module: monitors the air cleanliness of the storage area of ​​sterilized instruments. If the air cleanliness exceeds the preset cleanliness threshold and indicates the risk of secondary contamination, it triggers a re-evaluation of the priority of conflicting tasks.

[0059] Resource allocation module: based on the priority re-evaluation results and the spatial distribution map of disinfection equipment, it updates the spatiotemporal resource conflict path and dynamically allocates disinfection resources.

[0060] Obtain multi-source real-time information from the disinfection supply center, including future equipment use needs, equipment infection risk level, equipment collaborative use information, and disinfection equipment spatial distribution map, including:

[0061] The specific process of obtaining multi-source real-time information from the disinfection supply center includes the following steps: first, obtain the instrument disinfection request data submitted by each department. The instrument disinfection request data is generated by the disinfection task submission interface of the hospital information management system, including the instrument type, quantity and expected disinfection completion time. The instrument type is coded according to the hospital instrument classification standard. For example, code A001 represents a scalpel and B002 represents a hemostatic forceps. The expected disinfection completion time is manually input by the department according to the surgical schedule or automatically generated by the system in association with the surgical plan.

[0062] Extract future surgery scheduling data from the hospital information management system. Future surgery scheduling data includes the types of surgeries planned to be performed by each department in the next 24 hours, operating room allocations, and a list of instruments expected to be used. By parsing the list of instruments in the surgery scheduling data, extract the types and quantities of instruments required for each surgery, and summarize and generate future instrument usage requirements. For example, if the orthopedic surgery schedule indicates that 5 A001 scalpels and 2 sets of C003 orthopedic drills are required, the corresponding statistics are future demand for A001 instruments +5, and future demand for C003 instruments +2.

[0063] Retrieve the preset association table between instrument type and infection risk level. The preset association table is developed by the hospital infection management department based on the clinical use scenarios of the instruments and stored in the database. The instrument type code in the association table corresponds to the infection risk level, which is divided into three levels: high risk, medium risk, and low risk. For example, type A001 scalpel is defined as a high risk level because it directly contacts the patient's blood, and type D004 tweezers are defined as a low risk level because they only contact the sterile area. Query the table according to the instrument type code in the current disinfection task to determine the corresponding instrument infection risk level.

[0064] Statistics are collected on the frequency of collaborative use of instruments in historical department joint surgery records. Historical department joint surgery records are stored in the surgery log database of the hospital information management system. The cross-department call records of instruments in multi-department joint surgery in the past year are recorded. Statistics are collected on the number of applications for the same type of instrument by different departments in the same time period. Information on collaborative use of instruments between departments is generated. For example, if the frequency of cardiac surgery and the emergency department jointly applying for A001 scalpels in joint surgery is an average of 3 times a day, it is marked as the cardiac surgery-emergency department collaborative frequency of 3 times / day.

[0065] The real-time location coordinates and transportation path topology data of the disinfection equipment are collected. The real-time location coordinates are obtained through the RFID positioning tags installed on the disinfection equipment, with a positioning accuracy of 0.5 meters. The transportation path topology data includes the floor plan of the disinfection supply center, corridor coordinates and elevator distribution information. By superimposing the real-time location coordinates and topological data, a spatial distribution map of the disinfection equipment is constructed. For example, the current coordinates of equipment number X1 are (102, 205), corresponding to shelf No. 3 in the sterilization area in the plan view. The coordinates of equipment number X2 are (305, 418), corresponding to the elevator near the orthopedic department in the transportation path.

[0066] Among them, the path topology data can be updated every quarter through a laser surveyor and synchronized with the hospital infrastructure management system to ensure the accuracy of the floor plan and channel coordinates.

[0067] The expected disinfection completion time in the instrument disinfection request data is compared with the surgery scheduling time in the future instrument usage demand. If the expected completion time of a certain instrument is earlier than its associated surgery scheduling time, the instrument demand is determined to be an urgent task.

[0068] The collaborative use information of equipment between departments is used to identify high-frequency collaborative department combinations. For example, if the collaborative frequency of the cardiac surgery-emergency department combination exceeds the threshold of 5 times / day, it is marked as a high-intensity collaborative pair, and shared equipment resources are allocated priority in subsequent task scheduling.

[0069] The transportation path topology data in the spatial distribution map of disinfection equipment includes path distance, traffic priority (such as the weight of the dedicated surgery channel is higher than that of the ordinary corridor) and real-time crowd density. The path topology data is used to calculate the shortest transportation time for different equipment to be dispatched to the target department. For example, the shortest path for equipment X1 from the sterilization area to the cardiac surgery department is directly through Corridor 3, which takes 2 minutes, while equipment X2 needs to bypass the dedicated surgery channel, which takes 3.5 minutes.

[0070] The preset correlation table of device infection risk levels is formulated based on the "Technical Specifications for Disinfection of Medical Institutions" issued by the state. The disinfection parameters corresponding to high-risk devices must meet the pressure steam sterilization temperature of 134°C and time of 5 minutes. The medium-risk devices are 121°C and time of 15 minutes. Low-risk devices can be sterilized by low-temperature plasma.

[0071] The analysis process of future equipment usage demand includes time slice division, dividing the next 24 hours into 2-hour periods and counting the total demand for each equipment type in each period. For example, the demand for A001 scalpels is 8 in the 8:00-10:00 period and 6 in the 10:00-12:00 period, generating a demand time series distribution curve.

[0072] Determine the urgency of device reuse based on the temporal distribution of future device use needs and the risk level of device infection, including:

[0073] The specific process of determining the urgency of instrument reuse includes the following steps: dividing the temporal distribution of future instrument usage demand into multiple continuous time periods according to preset time slices, the length of the preset time slices is determined according to the instrument call interval of the hospital's surgical schedule, and by analyzing the fluctuations in the hourly instrument application volume in historical surgical records, selecting the time unit with stable demand fluctuations as the time period length. For example, if the peak of surgery in a hospital is concentrated in the morning and the instrument application volume changes significantly every 2 hours, the time slice is set to 2 hours, and the division results are 8:00-10:00, 10:00-12:00 and other time periods.

[0074] When counting the total demand for each type of instrument in each time period, extract the instrument list for each operation from the parsed surgical scheduling data, and add up the quantities by instrument type code. For example, when parsing the scheduling data for 10 orthopedic surgeries in the 8:00-10:00 time period, it is found that the total demand for A001 scalpels is 10, and the total demand for C003 orthopedic drills is 6 sets.

[0075] The risk weighting coefficient of each device type is set according to the device infection risk level. The device infection risk level is set according to the classification standard of medical devices in the "Technical Specifications for Disinfection of Medical Institutions". High-risk devices include devices that contact patients' damaged skin, mucous membranes or invade sterile tissues. Medium-risk devices include non-invasive devices that contact patients' intact skin. Low-risk devices include devices that only contact clean items. Based on this standard, the Hospital Infection Management Department formulates a mapping table between device types and risk levels and sets weighting coefficients. For example, the risk weighting coefficient of high-risk devices is 1.5, medium-risk is 1.2, and low-risk is 1.0. In the mapping table, the A001 scalpel code is associated with a high risk coefficient of 1.5, and the B002 hemostatic forceps code is associated with a low risk coefficient of 1.0.

[0076] The total demand for each type of device in the same time period is multiplied by its corresponding risk weighting coefficient to obtain the weighted demand value of each device type. For example, in the 8:00-10:00 period, the demand for A001 scalpels is 10, and the weighted demand value is 15 after multiplying by the high risk coefficient of 1.5. The demand for B002 hemostatic forceps is 20, and the weighted demand value is 20 after multiplying by the low risk coefficient of 1.0. When accumulating the weighted demand values ​​of the same device type in all time periods, the calculation results of each time period are summarized by device type code. For example, the weighted value of A001 scalpels from 8:00-10:00 is 15, and from 10:00-12:00 is 18, so the cumulative urgency score is 33.

[0077] The combined logic of time period division and risk weighting solves the defects of single-dimensional decision-making in traditional scheduling methods. For example, traditional methods only sort by application time or quantity, which may ignore the timeliness requirements of high-risk devices. In this solution, although the total demand for B002 hemostatic forceps is higher, due to its low risk factor, the cumulative score of 44 may be lower than that of A001 scalpel 33. However, after combining the threshold comparison, if the A001 score exceeds its threshold of 30, it is still marked as a high-urgency task to ensure that infection risk control takes precedence over pure quantity requirements.

[0078] Determine the degree of departmental collaboration based on the collaborative use information of the equipment, and mark the department nodes in the current conflicting tasks, including:

[0079] The specific implementation process of determining the degree of departmental collaboration and marking department nodes includes: extracting historical departmental joint surgery records stored in the hospital information management system, where the records contain department number, instrument type code, application timestamp, and surgery type field. For example, the record "K01 (cardiac surgery), K02 (emergency department), A001 (scalpel), 2023-05-10 09:00:00, emergency surgery" means that departments K01 and K02 jointly applied for A001 scalpel for emergency surgery at 9:00.

[0080] Count the number of events in which the same device type is applied for consecutively by the same department combination within the preset time window (24 hours by default) with an interval less than the preset interval threshold (30 minutes by default). For example, departments K01-K02 apply for A001 scalpel three times at 9:00, 9:15, and 9:30 on May 10, 2023. The adjacent application intervals are 15 minutes and 15 minutes, respectively, both less than 30 minutes, which are counted as 3 consecutive triggers.

[0081] The collaborative time sensitivity parameter is set according to the median of the continuous application intervals for the same type of equipment by the same department combination in historical data. The specific method is: after excluding abnormal data with an interval of more than 24 hours, calculate the median of the remaining intervals. For example, the median interval of 100 applications for A001 scalpels by departments K01-K02 is 15 minutes, so its sensitivity parameter is set to 15 minutes. If the actual application interval is ≤15 minutes, it is marked as a high-sensitivity event. After identifying all high-sensitivity department combinations, a closeness hierarchy list is generated in descending order of the number of continuous triggers. For example, departments K01-K02 trigger 5 high-sensitivity events within 24 hours, and departments K03-K04 trigger 3 times, then the hierarchy list is K01-K02 (5 times), K03-K04 (3 times).

[0082] When analyzing the historical collaboration density level of the equipment application department in the current conflict task, if its associated department ranks in the top N in the hierarchy list (N is set proportionally according to the total number of departments, N=10 when there are 50 departments, and N=5 when there are 20 departments), it is marked as a key collaboration node. For example, in the current conflict task, department K01 applies for A001 scalpel, and its associated department K02 ranks first in the hierarchy list (N=5), then K02 is marked as a key node.

[0083] The resource allocation path is dynamically adjusted according to the key node's closeness level difference (the difference between the current node ranking and other node rankings). The key node's closeness level difference threshold is set according to the 75% quantile of the level difference in the historical tasks. For example, if the 75% quantile is 2 for the past 100 tasks, the difference threshold is set to 2. If K01-K02 ranks first and K01-K05 ranks fourth in the current task, and the key node's closeness level difference 3≥2, the path optimization is triggered, and the A001 scalpel is preferentially allocated to the K01-K02 path, and the path is marked as a high-priority channel in the spatial distribution map of disinfection equipment.

[0084] The preset interval threshold is set based on the turnover requirements of the hospital's routine surgeries. For example, if an operation takes an average of 1 hour, a 30-minute interval can cover the instrument preparation time for adjacent operations. The median calculation of the collaborative time sensitivity parameter excludes abnormal intervals (such as > 24 hours) caused by equipment failure or system errors to ensure the objectivity of the parameters. The 75% quantile calculation of the hierarchical difference adjustment threshold is based on the historical task data of the past three months and is updated monthly to ensure timeliness. If there is no historical data (such as a newly established department), the default parameters for the entire hospital (interval threshold of 30 minutes, sensitivity parameter of 30 minutes) are used until data accumulation is completed.

[0085] When the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; otherwise, the conflicting tasks are ranked based on the closeness of departmental collaboration, including:

[0086] The specific implementation process of setting priorities and hierarchical rankings includes: comparing the cumulative urgency score with the dynamic urgency threshold. The dynamic urgency threshold is set according to the emergency task response plan formulated by the hospital infection management department. The specific rule is to take 120% of the average daily peak demand for the same type of equipment in the same historical period (such as the past three months). For example, the average daily peak demand for A001 scalpels in the second quarter of 2023 is 20, and the dynamic urgency threshold is set to 24.

[0087] When the cumulative urgency score exceeds the dynamic urgency threshold, for example, the current cumulative score of the A001 scalpel is 26 (generated by the weighted calculation of the time period demand), which exceeds the threshold of 24, the sterilization priority of the associated conflicting tasks will be marked as the highest level, and the dedicated sterilization equipment resources reserved for the emergency task will be locked. The dedicated equipment resources are high-temperature sterilization cabinets (equipment number X1), and its parameters are set to 134°C and 5 minutes. Other tasks shall not occupy it until the emergency task is completed.

[0088] When the cumulative urgency score does not exceed the dynamic urgency threshold, for example, the cumulative score of B002 hemostatic forceps is 18, and the threshold 20 is not exceeded, the collaboration closeness level data of the instrument application department in the conflicting task is extracted. The collaboration closeness level data comes from the department combination closeness ranking table updated weekly. For example, department K01-K02 (cardiac surgery-emergency department) ranks first in the collaboration closeness level of A001 scalpel, and department K03-K04 (orthopedics-general surgery) ranks third. The task sequence generated in descending order of the level ranking is K01-K02 task and K03-K04 task.

[0089] When calculating the difference in the level of collaboration closeness of adjacent tasks in a task sequence, for example, the difference between K01-K02 (level 1) and K03-K04 (level 3) in the task sequence is 2, and the difference threshold is set according to the distribution of the level differences in historical tasks. The specific rule is to take the 75% quantile of the level differences of the past 100 tasks. For example, if the 75% quantile in the statistical result is 1, the split threshold is set to 1. If the current difference 2 exceeds the threshold 1, the high difference tasks are split into independent processing groups, for example, the K01-K02 tasks and the K03-K04 tasks are split into two groups for independent processing.

[0090] When merging disinfection batches based on the compatibility of sterilization parameters of instruments in independent treatment groups, the compatibility is determined based on the operating specifications of the hospital's disinfection supply center, which requires that the sterilization temperature deviation of instruments in the same batch should not exceed ±2°C and the sterilization time deviation should not exceed ±10%. For example, A001 scalpels (134°C, 5 minutes) and C003 orthopedic drills (134°C, 6 minutes) can be combined into the same batch, share sterilization equipment X1 and be transported synchronously, while B002 hemostatic forceps (121°C, 15 minutes) are shipped separately due to parameter differences.

[0091] The 120% ratio of the dynamic urgency threshold is set according to the emergency response level of the hospital infection management department for public health emergencies. When the cumulative score exceeds the threshold, the red warning mechanism is triggered and special equipment resources are forced to be used. The split threshold of the collaboration level difference is recalculated every month based on the latest 30-day task data. For example, if the 75% quantile of the level difference in a certain month is updated to 2, the split threshold is adjusted to 2 synchronously. If there is no historical data support (such as the newly introduced D004 endoscope), the default threshold of the same type of equipment is used. For example, the default threshold of endoscope equipment is 130% of the historical average daily demand.

[0092] The compatibility of sterilization parameters needs to be manually reviewed and confirmed. For example, after the system automatically merges A001 and C003 into the same batch, the supervisor of the disinfection supply center needs to review whether the parameter deviation (temperature 0°C, time +1 minute) is within the allowable range on the operation interface, and execute the batch operation after confirmation.

[0093] Monitor the air cleanliness of the sterilized equipment storage area. If the air cleanliness exceeds the preset cleanliness threshold and indicates the risk of secondary contamination, trigger a re-evaluation of the priority of conflicting tasks, including:

[0094] The specific implementation process of triggering priority re-evaluation includes: obtaining air cleanliness monitoring data of the storage area of ​​the instrument after disinfection. The air cleanliness monitoring data is collected in real time by the suspended particle counter and microbial sampler deployed in the storage area, and includes two indicators: suspended particle concentration and microbial colony count. The suspended particle concentration is measured in particles per cubic meter, and the microbial colony count is measured in colony-forming units per cubic meter.

[0095] The suspended particle concentration and the number of microbial colonies are compared with the preset clean threshold intervals. The preset clean threshold intervals are set according to the national standard "Management Specifications for Hospital Sterilization Supply Centers". The suspended particle concentration threshold interval is 0-35,000 particles / cubic meter, and the microbial colony count threshold interval is 0-200 CFU / cubic meter. If any indicator exceeds the upper limit of the threshold interval, for example, the suspended particle concentration detection value is 42,000 particles / cubic meter, and the microbial colony count is 180 CFU / cubic meter, it is marked as a secondary contamination risk event, and the start time and current time of the event are recorded to calculate the duration.

[0096] When calculating the pollution risk diffusion rate based on the duration of secondary pollution risk events, the pollution risk diffusion rate is the growth of pollution indicators per unit time.

[0097] The specific calculation method for the pollution risk diffusion rate is: (current pollution index value - initial pollution index value) / duration.

[0098] For example, if the initial suspended particle concentration in a storage area is 35,000 particles / m3 and rises to 42,000 particles / m3 after 3 hours, the diffusion rate is (4.2-3.5) / 3=2,300 particles / (m3·hour). If the number of microbial colonies rises from 180 CFU / m3 to 220 CFU / m3 in the same event, the diffusion rate is (220-180) / 3≈13.3 CFU / (m3·hour). The higher value of the diffusion rates of the two indicators is taken as the final contamination risk diffusion rate.

[0099] When extracting the task list involving the risk storage area in the current conflicting task queue, all tasks marked as "unfinished" in the task management system of the disinfection supply center and whose associated equipment storage locations match the risk storage area are included in the list. For example, if a contamination risk event occurs in storage area A, and there are 5 tasks in the task queue involving equipment storage in area A, then these 5 tasks are extracted to generate a list. When generating a reassessment task sequence from high to low according to the contamination risk diffusion rate, for example, the diffusion rate of task 1 is 2,300 grains / (cubic meter·hour), task 2 is 1,500 grains / (cubic meter·hour), and task 3 is 1,000 grains / (cubic meter·hour), then the reassessment task sequence is sorted as task 1, task 2, and task 3.

[0100] The calculation of the pollution risk diffusion rate needs to exclude abnormal data caused by equipment failure or instantaneous fluctuations. For example, if the suspended particle concentration suddenly increases from 35,000 to 50,000 within 5 minutes and then immediately drops back, such data will be deemed invalid and re-collected.

[0101] The extraction rules of the task list include strict matching of the equipment storage location and the risk area. For example, the storage location code of the equipment in the task must be exactly the same as the code of the risk storage area to avoid mistaken association with tasks in other areas.

[0102] The duration is calculated to the nearest minute. For example, if the risk event lasts from 9:00 to 10:30, the duration is 1.5 hours. If the pollution index fluctuates and exceeds the threshold during the duration, the duration is calculated based on the time when it last exceeded the threshold. For example, if the suspended particle concentration exceeds the threshold from 9:00 to 9:30, falls back to the threshold from 9:30 to 10:00, and exceeds the threshold again at 10:00, the duration is calculated as 1 hour from 9:00 to 10:00. The rule for selecting higher values ​​of the contamination risk diffusion rate is to give priority to indicators that have a greater impact on device safety. For example, the diffusion rate of excessive microbial colony counts has a higher priority than the suspended particle concentration.

[0103] Based on the priority re-evaluation results and the spatial distribution map of disinfection equipment, the spatial and temporal resource conflict paths are updated and disinfection resources are dynamically allocated, including:

[0104] The specific implementation process of updating the spatiotemporal resource conflict path and dynamically allocating disinfection resources includes: extracting the reassessment task sequence in the priority reassessment result and the real-time location coordinates of the equipment in the spatial distribution map of the disinfection equipment, the reassessment task sequence comes from the task list generated in step S5 and arranged in descending order according to the diffusion rate of the pollution risk, such as task 1 (diffusion rate 2,300 particles / hour), task 2 (1,500 particles / hour), and task 3 (1,000 particles / hour), and the real-time location coordinates of the equipment are collected in real time through the RFID positioning tags deployed on the disinfection equipment, for example, the coordinates of the equipment X1 are (102,205), and the coordinates of the equipment X2 are (305,418).

[0105] The shortest transportation time for each device to the target area is calculated based on the real-time location coordinates of the equipment and the path topology data of the storage area associated with the task. The path topology data includes floor plans, corridor coordinates, and elevator distribution information. For example, the shortest path for equipment X1 from coordinates (102,205) to storage area A is directly through corridor 3, which takes 2 minutes. Equipment X2 needs to bypass the dedicated surgery channel, which takes 3.5 minutes.

[0106] When generating an emergency task group according to the order of the re-evaluated task sequence, Task 1, Task 2, and Task 3 are included in the emergency task group in the original sequence. Equipment whose shortest transportation time is less than the preset response threshold is marked as an available resource. The preset response threshold is set according to the 75% quantile of the historical transportation time. For example, if the transportation time of equipment to various regions in the past three months is counted and the 75% quantile is 3 minutes, then the response threshold is set to 3 minutes. If the transportation time of equipment X1 is 2 minutes < 3 minutes, it is marked as an available resource, and if the transportation time of equipment X2 is 3.5 minutes > 3 minutes, it is marked as an unavailable resource.

[0107] The device allocation priority is adjusted based on the dynamic load factor of available resources. The dynamic load factor is the ratio of the remaining time of the device's current task queue to the maximum load time. For example, the remaining time of the current task queue of device X1 is 1 hour, and the maximum load time is 8 hours. The dynamic load factor is 1 / 8=0.125. The remaining time of device X3 is 2 hours, and the maximum load time is 6 hours. The load factor is 2 / 6≈0.333. The lower the load factor, the higher the priority.

[0108] The remaining time of the current task queue of the equipment is obtained in real time from the disinfection equipment status monitoring system. The maximum load time is set according to the technical manual provided by the equipment manufacturer. For example, the maximum load time of the high-temperature sterilizer X1 is 8 hours.

[0109] When tasks with compatible sterilization parameters in the merged emergency task group are from the same batch, the compatibility of sterilization parameters is determined according to the national standard "Operation Specifications for Hospital Sterilization Supply Centers", which requires that the sterilization temperature deviation of instruments in the same batch does not exceed ±2°C and the sterilization time deviation does not exceed ±10%. For example, Task 1 (A001 scalpel, 134°C, 5 minutes) and Task 3 (C003 orthopedic drill, 134°C, 6 minutes) have a temperature deviation of 0°C and a time deviation of +1 minute (+20%). They cannot be merged because the time deviation exceeds the limit, while Task 2 (D004 forceps, 134°C, 5 minutes) can be merged with Task 1 into the same batch. When executing batch tasks in descending order of equipment allocation priority, the priority of Equipment X1 0.125 is higher than that of Equipment X3 0.333. The merged batch of Tasks 1-2 is preferentially assigned to Equipment X1 for execution, and Task 3 is assigned to Equipment X3 alone.

[0110] The monthly update rule for the preset response threshold is to take the 75% quantile of the latest 30-day transportation time. For example, if the statistical quantile drops to 2.5 minutes in a certain month, the threshold is synchronously updated to 2.5 minutes. The calculation of the dynamic load factor excludes abnormal data during the equipment maintenance period. For example, the task queue data of the daily fixed maintenance period (14:00-14:30) of equipment X1 is not included in the calculation. The compatibility determination of sterilization parameters requires manual review. For example, after the system automatically determines that tasks 1-2 cannot be merged, the temperature deviation is ±2°C and the time deviation is ±10%. Batches cannot be merged if the range is exceeded.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0112] It should be noted that the present invention can be deployed on the device itself to realize embedded applications, and can also be run on a PC or other terminal with a user interface, so as to meet various hardware environments and usage requirements.

[0113] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0116] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0118] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0120] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A disinfection supply center workflow optimization system based on big data analysis, characterized in that: include: Multi-source acquisition module: obtain multi-source real-time information from the disinfection supply center, including future equipment use needs, equipment infection risk level, equipment collaborative use information and disinfection equipment spatial distribution map; Urgency analysis module: Determine the urgency of device reuse based on the temporal distribution of future device usage needs and the device infection risk level; Collaboration analysis module: Determine the degree of departmental collaboration based on the collaborative use information of equipment, and mark the department nodes in the current conflicting tasks; Dynamic sorting module: When the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; Otherwise, the conflicting tasks are ranked hierarchically based on the closeness of departmental collaboration; Environmental monitoring module: monitors the air cleanliness of the storage area of ​​sterilized instruments. If the air cleanliness exceeds the preset cleanliness threshold and indicates the risk of secondary contamination, it triggers a re-evaluation of the priority of conflicting tasks. Resource allocation module: based on the priority re-evaluation results and the spatial distribution map of disinfection equipment, it updates the spatiotemporal resource conflict path and dynamically allocates disinfection resources.

2. According to claim 1, a disinfection supply center workflow optimization system based on big data analysis is characterized in that: Get real-time information from multiple sources in the sterile supply center, including: Obtain the instrument disinfection request data submitted by each department, which includes instrument type, quantity and expected disinfection completion time; Extract future surgery scheduling data from the hospital information management system and analyze future equipment usage requirements in the surgery scheduling data; Retrieve the preset association table between device type and infection risk level to determine the device infection risk level of the currently disinfected device; Count the frequency of collaborative use of instruments in historical department joint surgery records and generate information on collaborative use of instruments between departments; Collect the real-time location coordinates and transportation route topology data of disinfection equipment to build a spatial distribution map of disinfection equipment.

3. The disinfection supply center workflow optimization system based on big data analysis according to claim 1, characterized in that: Determine the urgency of device reuse based on the temporal distribution of future device use needs and the risk level of device infection, including: Divide the temporal distribution of future equipment usage demand into multiple continuous time periods according to preset time slices, and count the total demand for each equipment type in each time period; Set the risk weighting coefficient for each device type according to the device infection risk level; Multiply the total demand of each device type in the same period by its corresponding risk weighting coefficient to obtain the weighted demand value of each device type; The weighted demand values ​​of the same device type in all time periods are accumulated to generate a cumulative urgency score for the corresponding device type to evaluate the urgency of device reuse.

4. The disinfection supply center workflow optimization system based on big data analysis according to claim 3 is characterized in that: The risk weighting coefficients for each device type are set as follows: high risk level corresponds to the first weighting coefficient, medium risk level corresponds to the second weighting coefficient, and low risk level corresponds to the third weighting coefficient.

5. The disinfection supply center workflow optimization system based on big data analysis according to claim 1, characterized in that: Determine the degree of departmental collaboration based on the collaborative use information of the equipment, and mark the department nodes in the current conflicting tasks, including: Extract collaborative events of the same instrument type from historical department joint surgery records, and count the number of consecutive triggering of collaborative events for each pair of department combinations within the preset time window; The coordination time sensitivity parameter is set according to the time interval distribution law of coordination events, and coordination events with continuous triggering intervals less than a preset threshold are marked with high sensitivity; Identify department combinations with high-sensitivity markers and generate department collaboration levels by sorting them according to the number of consecutive triggering of collaborative events; Analyze the historical collaboration closeness levels of the equipment application departments in the current conflicting task. If there are several combinations ranked in the top closeness levels in the corresponding related departments, mark them as key collaboration nodes. The resource allocation path of conflicting tasks is dynamically adjusted according to the difference in the closeness levels of key collaborative nodes, giving priority to meeting the equipment reuse needs of high-closeness level combinations.

6. The disinfection supply center workflow optimization system based on big data analysis according to claim 1, characterized in that: When the urgency of device reuse exceeds the dynamic urgency threshold, the priority of the corresponding conflicting task is set to the highest; Otherwise, the conflicting tasks are ranked based on the closeness of departmental collaboration, including: Compare the cumulative urgency score with the dynamic urgency threshold, which is set based on the average daily demand for the same type of device during the same period in history; When the cumulative urgency score exceeds the dynamic urgency threshold, the sterilization priority of the associated conflicting tasks is marked as the highest level and the dedicated sterilization equipment resources are locked; When the cumulative urgency score does not exceed the dynamic urgency threshold, the collaboration level of the equipment application departments in the conflicting tasks is extracted, and the task sequence is generated in descending order of the level ranking; Calculate the collaboration density level difference of adjacent tasks in the task sequence. If the collaboration density level difference exceeds the preset split threshold, split them into independent processing groups. The sterilization batches are merged based on the compatibility of the sterilization parameters of the instruments in the independent processing groups. The tasks in the same batch share the sterilization equipment and execute the transportation instructions synchronously.

7. The disinfection supply center workflow optimization system based on big data analysis according to claim 1, characterized in that: Monitor the air cleanliness of the sterilized equipment storage area. If the air cleanliness exceeds the preset cleanliness threshold and indicates the risk of secondary contamination, trigger a re-evaluation of the priority of conflicting tasks, including: Obtain air cleanliness monitoring data of the storage area of ​​sterilized instruments, including suspended particle concentration and microbial colony count; If any of the suspended particle concentration and microbial colony count exceeds the upper limit of the threshold range, it will be marked as a secondary pollution risk event; The pollution risk diffusion rate is calculated based on the duration of the secondary pollution risk event. The pollution risk diffusion rate is the growth of the pollution index per unit time. Extract the task list involving the risk storage area in the current conflicting task queue, and generate a reassessment task sequence from high to low according to the pollution risk diffusion rate.

8. The disinfection supply center workflow optimization system based on big data analysis according to claim 1, characterized in that: Based on the priority re-evaluation results and the spatial distribution map of disinfection equipment, the spatial and temporal resource conflict paths are updated and disinfection resources are dynamically allocated, including: Extract the re-evaluation task sequence in the priority re-evaluation result and the real-time location coordinates of the equipment in the spatial distribution map of the disinfection equipment; Calculate the shortest transportation time from each device to the target area based on the real-time location coordinates of the device and the path topology data of the task-related storage area; Generate an emergency task group according to the order of the re-evaluated task sequence, and mark the equipment with the shortest transportation time less than the preset response threshold as available resources; Adjust device allocation priority based on the dynamic load factor of available resources. The dynamic load factor is the ratio of the remaining time in the device's current task queue to the maximum load time. Merge the tasks with compatible sterilization parameters in the emergency task group into the same batch, and execute the batch tasks in descending order of equipment allocation priority.

Images