Hemodialysis consumable stock management and allocation method, device, equipment and medium

Abstract

The invention relates to a hemodialysis consumable stock management and allocation method and device, equipment and a medium. Firstly, historical treatment data and consumable use records of a patient are obtained and processed to obtain a consumable consumption predicted value. And then, combining the predicted value with the current inventory data to generate a predicted inventory, performing judgment, and once the predicted inventory is lower than a preset threshold value, generating a consumable supplement plan. And integrating cross-regional inventory data and transportation constraint conditions based on the supplementary plan to form a preliminary scheduling scheme. And matching the preliminary scheduling scheme with the patient treatment data to obtain a resource configuration adjustment suggestion. And finally, inputting the data in the adjustment suggestion into the inventory prediction model to obtain a dynamic replenishment strategy table of the next period. The table is used for judging whether a certain type of consumables have shortage risks or not, and if yes, a hierarchical management execution scheme is generated. Accurate prediction of consumable consumption of each hemodialysis center is realized, a dynamic adjustment mechanism can be triggered in time, and the risk of treatment delay caused by consumable shortage is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of medical resource management, and particularly relates to a hemodialysis consumable inventory management and allocation method, device, equipment and medium. Background Art

[0002] With the development of medical resource management technology, hemodialysis consumable inventory management and allocation technology has emerged. With the continuous growth of the number of nephropathy patients, the demand for hemodialysis treatment has risen sharply, which poses a severe challenge to the supply guarantee of hemodialysis consumables. The traditional hemodialysis consumable inventory management and allocation mode relies on manual experience, not only unable to accurately predict the consumption of consumables, but also the inventory data transmission is lagged, resulting in frequent shortages or overstocks of consumables in each hemodialysis center. Once there is a shortage of consumables, it will directly affect the treatment process of patients and even endanger their lives; while overstocked consumables will occupy a large amount of funds and storage space, causing waste of medical resources. In addition, the cross-regional hemodialysis consumable scheduling lacks systematic planning and is difficult to meet the actual needs of different regions. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method that can achieve accurate inventory management and efficient allocation of hemodialysis consumables, and improve the quality of medical services and the utilization efficiency of resources, a hemodialysis consumable inventory management and allocation method, device, equipment and medium.

[0004] In a first aspect, the present application provides a hemodialysis consumable inventory management and allocation method, including:

[0005] Obtain the historical treatment data of patients and the consumption records of consumables; use the time series analysis algorithm to process the historical treatment data and the consumption records of consumables to obtain the predicted consumption values of consumables in each hemodialysis center.

[0006] Generate a predicted inventory based on the predicted consumption value and the current inventory data and make a judgment. If the predicted inventory is lower than the preset threshold, trigger a dynamic adjustment mechanism to generate a consumable replenishment plan.

[0007] Extract multi-point scheduling requirements based on the replenishment plan and use the distributed database technology to integrate cross-regional inventory data and transportation constraints to obtain a preliminary scheduling plan.

[0008] Match the patient treatment data according to the preliminary scheduling plan to analyze abnormal consumption or scheduling deviation, and obtain resource allocation adjustment suggestions.

[0009] Input the data in the adjustment suggestions into the inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to judge whether there is a shortage risk for a certain type of consumable. If so, allocate it to the high-demand center according to the treatment safety priority to generate a hierarchical management implementation plan.

[0010] In one embodiment, historical treatment data and consumable usage records are processed using a time series analysis algorithm to obtain the consumable consumption prediction values for each hemodialysis center, including:

[0011] Extract the historical treatment data and consumable usage records to obtain the consumable consumption time series.

[0012] Use the time series analysis algorithm to perform periodic decomposition on the consumable consumption time series to obtain a trend term, a seasonal term, and a residual term.

[0013] Construct a consumable consumption prediction model based on the trend term and the seasonal term to obtain the consumable consumption prediction values for each hemodialysis center.

[0014] Obtain the fluctuation range of the residual term and determine whether the residual term exceeds a preset fluctuation threshold; if the residual term exceeds the fluctuation threshold, it is marked as an abnormal consumption event.

[0015] Associate the abnormal consumption event with the corresponding hemodialysis center number and treatment parameters to obtain a list of abnormal consumption events.

[0016] Adjust the parameters of the consumable consumption prediction model based on the list of abnormal consumption events to obtain the consumable consumption prediction values for each hemodialysis center.

[0017] In one embodiment, constructing a consumable consumption prediction model based on the trend term and the seasonal term to obtain the consumable consumption prediction values for each hemodialysis center, including:

[0018] Correlate and match the trend term with the equipment maintenance records of the hemodialysis center. If the slope of the trend term changes after the maintenance time, a consumable consumption rate correction instruction is triggered.

[0019] Adjust the cycle parameters of the seasonal term according to the correction instruction to generate an updated consumable consumption prediction curve.

[0020] Perform clustering analysis on the prediction curve using a clustering algorithm to divide it into different data clusters, and obtain dynamic threshold parameters based on the boundary characteristics of the remaining clusters.

[0021] Input the dynamic threshold parameters into the consumable consumption prediction model and calculate the consumable consumption prediction values for each hemodialysis center using a formula.

[0022] In one embodiment, the consumable consumption prediction value is calculated by the following formula:

[0023]

[0024] Where, P pred represents the consumable consumption prediction value of the hemodialysis center, n represents the number of consumable types, C i represents the unit consumption of the i-th consumable, M iRepresents the patient quantity factor, D i Represents the department scale factor, α i , β i , γ i Respectively represent the weight coefficients of each factor.

[0025] In one embodiment, multi-point scheduling requirements are extracted based on a replenishment plan, and cross-regional inventory data and transportation constraint conditions are integrated using distributed database technology to obtain a preliminary scheduling plan, including:

[0026] Obtain the regional node information in the replenishment plan; the regional node information includes inventory identification codes of multiple geographical locations.

[0027] Obtain the time limit threshold and capacity upper limit in the transportation constraint conditions; the transportation constraint conditions are associated with the path topology.

[0028] Extract cross-regional inventory dynamic indicators according to the inventory identification codes, and generate a candidate transportation path set based on the inventory dynamic indicators and the time limit threshold; the candidate transportation path set carries the capacity upper limit and node load parameters.

[0029] Use the path scoring algorithm to screen the candidate transportation path set, and match the screened transportation paths with the multi-point scheduling requirements to obtain a preliminary scheduling plan with path allocation results;

[0030] The preliminary scheduling plan includes the inventory transfer volume and transportation batch numbers of each node.

[0031] In one embodiment, according to the preliminary scheduling plan, match the patient treatment data to analyze abnormal consumption or scheduling deviation, and obtain resource configuration adjustment suggestions, including:

[0032] Obtain the patient treatment data in the preliminary scheduling plan; the patient treatment data includes the usage duration of treatment equipment and the consumption of consumables.

[0033] Calculate according to the patient treatment data using a formula to obtain the equipment utilization rate deviation coefficient and the abnormal consumable consumption index.

[0034] Based on a preset threshold, judge the equipment utilization rate deviation coefficient. If it exceeds the preset threshold, obtain the department scheduling record corresponding to the treatment equipment.

[0035] Generate a dynamic resource allocation matrix according to the department scheduling record and the abnormal consumable consumption index.

[0036] Input the dynamic resource allocation matrix into the scheduling optimization model to obtain the equipment allocation path and the consumable replenishment list.

[0037] Update the preliminary scheduling plan according to the equipment allocation path and the consumable replenishment list to generate resource configuration adjustment suggestions.

[0038] In one embodiment, the data in the adjustment suggestion is input into an inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle, including:

[0039] Obtain the feature adjustment parameters and historical inventory data in the adjustment suggestion; the historical inventory data contains inventory change records for multiple cycles.

[0040] Allocate weights to the historical inventory data according to the feature adjustment parameters to obtain an adjusted input feature vector.

[0041] Input the input feature vector into the trained inventory prediction model to obtain a multi-dimensional prediction result; the multi-dimensional prediction result contains the inventory consumption rate and the replenishment demand interval.

[0042] Analyze the upper and lower limits of the inventory threshold of the target warehouse according to the replenishment demand interval and match them with the current inventory data to obtain a dynamic replenishment strategy table for the next cycle; the upper and lower limits of the inventory threshold correspond to the storage conditions of different product categories.

[0043] In a second aspect, the present application also provides a hemodialysis consumable inventory management and allocation device, which includes:

[0044] A data processing module, configured to obtain patient historical treatment data and consumable usage records; use a time series analysis algorithm to process the historical treatment data and consumable usage records to obtain the consumable consumption prediction values of each hemodialysis center.

[0045] A solution generation module, configured to generate a predicted inventory based on the consumable consumption prediction value and the current inventory data and make a judgment. If the predicted inventory is lower than a preset threshold, trigger a dynamic adjustment mechanism to generate a consumable replenishment plan; also configured to extract multi-point scheduling requirements based on the replenishment plan and use distributed database technology to integrate cross-regional inventory data and transportation constraint conditions to obtain a preliminary scheduling plan.

[0046] A replenishment transfer module, configured to match the patient treatment data according to the preliminary scheduling plan to analyze abnormal consumption or scheduling deviation to obtain a resource allocation adjustment suggestion; also configured to input the data in the adjustment suggestion into an inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to judge whether there is a shortage risk for a certain type of consumable. If so, allocate it to high-demand centers according to the treatment safety priority to generate a hierarchical management execution plan.

[0047] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the foregoing method is implemented.

[0048] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the foregoing method is implemented.

[0049] The above-mentioned hemodialysis consumable inventory management and allocation method, device, equipment and medium first obtain the patient's historical treatment data and consumable usage records, and process them with a time series analysis algorithm to obtain the consumable consumption prediction values of each hemodialysis center. Subsequently, the predicted inventory is generated by combining the consumable consumption prediction value and the current inventory data and judged. Once the predicted inventory is lower than the preset threshold, the dynamic adjustment mechanism is triggered to generate a consumable replenishment plan. Based on this replenishment plan, the multi-point scheduling requirements are extracted, and the distributed database technology is used to integrate the cross-regional inventory data and transportation constraints to form a preliminary scheduling plan. Then, the preliminary scheduling plan is matched with the patient's treatment data to analyze abnormal consumption or scheduling deviation, and suggestions for resource allocation adjustment are obtained. Finally, the data in the adjustment suggestions is input into the inventory prediction model to obtain the dynamic replenishment strategy table for the next cycle. This table is used to judge whether there is a shortage risk for a certain type of consumable. If so, it is allocated to the high-demand centers according to the treatment safety priority, and a hierarchical management execution plan is generated. It can accurately predict the consumable consumption of each hemodialysis center, trigger the dynamic adjustment mechanism in time, and reduce the risk of treatment delay caused by consumable shortage. It greatly improves the efficiency of cross-regional resource allocation and further optimizes the resource allocation. It can not only accurately judge the consumable shortage risk, but also allocate according to the treatment safety priority, ensure that the resource allocation is tilted towards the high-demand centers, improve the utilization efficiency of the overall medical resources, and help the refined and intelligent transformation of hemodialysis center management. Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 It is a flowchart of a hemodialysis consumable inventory management and allocation method provided by an embodiment of the present invention;

[0052] Figure 2 It is a flowchart of using a time series analysis algorithm to process historical treatment data and consumable usage records to obtain the consumable consumption prediction values of each hemodialysis center provided by an embodiment of the present invention;

[0053] Figure 3 It is a flowchart of matching the patient's treatment data according to the preliminary scheduling plan to analyze abnormal consumption or scheduling deviation to obtain suggestions for resource allocation adjustment provided by an embodiment of the present invention;

[0054] Figure 4 It is a structural block diagram of a hemodialysis consumable inventory management and allocation device provided by an embodiment of the present invention. Detailed implementation manners

[0055] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In one of the embodiments, as Figure 1 shown, the present application provides a hemodialysis consumable inventory management and allocation method, which may include the following steps:

[0057] Step S101, obtaining historical treatment data of patients and consumable usage records; processing the historical treatment data and consumable usage records by using a time series analysis algorithm to obtain the consumable consumption prediction values of each hemodialysis center.

[0058] Specifically, the historical treatment data covers detailed information such as treatment time, frequency, model of hemodialysis equipment used, and the usage quantity and specifications of various consumables during each treatment process. By establishing a data acquisition interface to dock with the information management systems of each hemodialysis center, the accuracy and integrity of the data are ensured. Then, using a time series analysis algorithm, in-depth analysis is carried out on the collected historical treatment data and consumable usage records. This algorithm arranges the data in chronological order, decomposes and models the trend, seasonal and periodic characteristics in the data, discovers the laws behind the data, and thus predicts the consumption quantity of different types of hemodialysis consumables in each hemodialysis center in the future for a period of time.

[0059] Step S102, generating a predicted inventory based on the consumable consumption prediction values and the current inventory data and making a judgment. If the predicted inventory is lower than a preset threshold, a dynamic adjustment mechanism is triggered to generate a consumable replenishment plan.

[0060] Based on the obtained consumable consumption prediction values of each hemodialysis center, comprehensive calculations are performed with the current inventory data to generate predicted inventory data. While generating the predicted inventory data, the system will compare the predicted inventory with a preset threshold. This preset threshold is determined based on the clinical treatment requirements of the hemodialysis center, emergency backup requirements, and past inventory management experience. Once the predicted inventory is lower than the preset threshold, the system will immediately trigger a dynamic adjustment mechanism to quickly generate a consumable replenishment plan, which details the types and quantities of consumables to be replenished and the estimated replenishment time, ensuring that the hemodialysis center has sufficient consumables to meet the treatment needs of patients.

[0061] Step S103, extracting multi-point scheduling requirements based on the replenishment plan and using distributed database technology to integrate cross-regional inventory data and transportation constraint conditions to obtain a preliminary scheduling plan.

[0062] Automatically extract multi-point scheduling requirements based on the generated consumable replenishment plan. By analyzing information such as the locations of hemodialysis centers, transportation distances, and traffic conditions, and combining the types and quantities of consumables required in the replenishment plan, clarify the scheduling tasks at each transportation node. At the same time, use distributed database technology to integrate cross-regional inventory data scattered in different regions, as well as transportation constraints such as time threshold during transportation and vehicle capacity limit. With the help of path planning algorithms, screen out the optimal solution from numerous feasible transportation paths to form a preliminary scheduling plan, effectively reducing transportation costs and improving resource allocation efficiency.

[0063] Step S104, match the preliminary scheduling plan with patient treatment data to analyze abnormal consumption or scheduling deviation, and obtain resource allocation adjustment suggestions.

[0064] Match and analyze the preliminary scheduling plan with the treatment data of patients. By studying data such as the usage duration of treatment equipment and the actual consumption of consumables during the patient's treatment process, calculate the deviation coefficient of equipment utilization rate and the abnormal consumption index of consumables. Once the deviation coefficient of equipment utilization rate exceeds the preset threshold, automatically obtain the department scheduling record corresponding to the treatment equipment. Based on the department scheduling record and the abnormal consumption index of consumables, construct a dynamic resource allocation matrix and input it into the scheduling optimization model. Through data analysis and operation, the model gives the equipment allocation path and the consumable replenishment list, and then optimizes the preliminary scheduling plan to obtain resource allocation adjustment suggestions, realizing the precise allocation of resources.

[0065] Step S105, input the data in the adjustment suggestions into the inventory prediction model to obtain the dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to judge whether there is a shortage risk for a certain type of consumable. If there is, allocate it to high-demand centers according to the treatment safety priority, and generate a hierarchical management implementation plan.

[0066] Combine the data in the resource allocation adjustment suggestions, including characteristic adjustment parameters such as the types and quantities of consumables and the allocation path, with historical inventory data. According to the importance of different data, assign weights to the historical inventory data to generate an adjusted input feature vector. Input this vector into an inventory prediction model trained with a large amount of data. The model outputs multi-dimensional prediction results through complex algorithm operations, including the inventory consumption rate and the replenishment demand interval. According to the replenishment demand interval, combined with the storage conditions of different goods categories, analyze the upper and lower limits of the inventory threshold of the target warehouse and match them with the current inventory data to generate the dynamic replenishment strategy table for the next cycle. When it is judged that there is a shortage risk for a certain type of consumable, allocate the consumable to high-demand centers according to the treatment safety priority and formulate a hierarchical management implementation plan to ensure the rationality and scientificity of resource allocation.

[0067] The above-mentioned hemodialysis consumable inventory management and allocation method first obtains the patient's historical treatment data and consumable usage records, and processes them using a time series analysis algorithm to obtain the consumable consumption prediction values for each hemodialysis center. Subsequently, the predicted inventory is generated by combining the consumable consumption prediction values with the current inventory data and judged. Once the predicted inventory is lower than the preset threshold, the dynamic adjustment mechanism is triggered to generate a consumable replenishment plan. Based on this replenishment plan, the multi-point scheduling requirements are extracted, and the distributed database technology is used to integrate the cross-regional inventory data and transportation constraints to form a preliminary scheduling plan. Then, the preliminary scheduling plan is matched with the patient's treatment data to analyze abnormal consumption or scheduling deviation, and suggestions for resource allocation adjustment are obtained. Finally, the data in the adjustment suggestions is input into the inventory prediction model to obtain the dynamic replenishment strategy table for the next cycle. This table is used to judge whether there is a shortage risk for a certain type of consumable. If so, it is allocated to the high-demand center according to the treatment safety priority, and a hierarchical management implementation plan is generated. It can accurately predict the consumable consumption of each hemodialysis center, trigger the dynamic adjustment mechanism in time, and reduce the risk of treatment delay caused by consumable shortage. It greatly improves the efficiency of cross-regional resource allocation and further optimizes the resource allocation. It can not only accurately judge the consumable shortage risk, but also allocate according to the treatment safety priority, ensure that the resource allocation tilts towards the high-demand center, improve the utilization efficiency of the overall medical resources, and help the refined and intelligent transformation of hemodialysis center management.

[0068] In one embodiment, as Figure 2 shown, using a time series analysis algorithm to process the historical treatment data and consumable usage records to obtain the consumable consumption prediction values for each hemodialysis center may include the following steps:

[0069] Step S201, extract the historical treatment data and consumable usage records to obtain the consumable consumption time series.

[0070] Step S202, use a time series analysis algorithm to perform cycle decomposition on the consumable consumption time series to obtain the trend term, seasonal term, and residual term.

[0071] Step S203, construct a consumable consumption prediction model based on the trend term and seasonal term to obtain the consumable consumption prediction values for each hemodialysis center.

[0072] Step S204, obtain the fluctuation range of the residual term, and judge whether the residual term exceeds the preset fluctuation threshold; if the residual term exceeds the fluctuation threshold, it is marked as an abnormal consumption event.

[0073] Step S205, associate the corresponding hemodialysis center number and treatment parameters with the abnormal consumption event to obtain a list of abnormal consumption events.

[0074] Step S206: Adjust the parameters of the consumable consumption prediction model based on the list of abnormal consumption events to obtain the consumable consumption prediction values for each hemodialysis center.

[0075] First, the system accurately extracts key information from a vast amount of historical treatment data and consumable usage records, and sorts out the consumable consumption time series. Immediately afterwards, it deeply analyzes this series using time series analysis algorithms. Through cycle decomposition, it decomposes it into a trend term, a seasonal term, and a residual term. Based on the trend term and the seasonal term, a consumable consumption prediction model is built to calculate the consumable consumption prediction values for each hemodialysis center. At the same time, the system will continuously obtain the fluctuation range of the residual term and compare it with a pre-set fluctuation threshold. Once the residual term exceeds the fluctuation threshold, it will immediately be marked as an abnormal consumption event. Subsequently, the system generates a detailed list of abnormal consumption events by associating the corresponding hemodialysis center numbers and treatment parameters, and based on this, optimizes and adjusts the parameters of the consumable consumption prediction model, and recalculates the consumable consumption prediction values for each hemodialysis center.

[0076] On the one hand, through the detailed decomposition and modeling of the consumable consumption time series, fully excavating the laws behind the data significantly improves the accuracy of consumable consumption prediction, provides strong data support for the inventory management and procurement plan formulation of hemodialysis centers, and effectively avoids the problems of consumable shortages or overstocking. On the other hand, the monitoring and handling of abnormal consumption events can timely detect potential abnormal situations during hemodialysis treatment, help managers timely adjust the consumable resource allocation strategy, ensure the smooth progress of hemodialysis treatment, further improve the operation management efficiency and medical service quality of hemodialysis centers, and promote the development of consumable management in the hemodialysis field towards intelligence and refinement.

[0077] In one embodiment, constructing a consumable consumption prediction model based on the trend term and the seasonal term to obtain the consumable consumption prediction values for each hemodialysis center may include the following steps:

[0078] Step S301: Correlate and match the trend term with the equipment maintenance records of the hemodialysis center. If the slope of the trend term changes after the maintenance time, a consumable consumption rate correction instruction is triggered.

[0079] Step S302: Adjust the cycle parameters of the seasonal term according to the correction instruction to generate an updated consumable consumption prediction curve.

[0080] Step S303: Use the clustering algorithm to perform clustering analysis on the prediction curve to divide it into different data clusters, and obtain dynamic threshold parameters according to the boundary characteristics of the remaining clusters.

[0081] Step S304: Input the dynamic threshold parameters into the consumable consumption prediction model and calculate the consumable consumption prediction values for each hemodialysis center using the formula.

[0082] First, associate the trend items with the equipment maintenance records of the hemodialysis center. Equipment maintenance can affect the hemodialysis process. When the system detects a change in slope of the trend items after the equipment maintenance time, it immediately triggers a consumable consumption rate correction instruction. Based on this instruction, the system makes corresponding adjustments to the cycle parameters of the seasonal items, thereby generating an updated consumable consumption prediction curve. To further improve the accuracy of the prediction, the system uses a clustering algorithm to perform clustering analysis on the updated prediction curve, divides the data into different data clusters, and obtains dynamic threshold parameters by deeply analyzing the boundary characteristics of the remaining clusters. Finally, input the dynamic threshold parameters into the pre-constructed consumable consumption prediction model and calculate using a specific formula to obtain more accurate consumable consumption prediction values for each hemodialysis center.

[0083] In this embodiment, by associating the trend items with the equipment maintenance records, fully considering the impact of equipment maintenance on consumable consumption, effectively correcting the consumable consumption rate, and greatly improving the accuracy and reliability of the prediction. Using a clustering algorithm to analyze the prediction curve and determining dynamic threshold parameters accordingly enables the prediction model to better adapt to consumable consumption changes in different stages and scenarios, avoiding the limitations brought by traditional fixed thresholds. This not only provides a more scientific basis for the inventory management of hemodialysis centers, reduces operating costs, but also helps to ensure the stable supply of hemodialysis treatment, and promotes the development of the hemodialysis consumable management mode towards the direction of intelligence and high efficiency.

[0084] In one of the embodiments, the consumable consumption prediction value can be calculated by the following formula:

[0085]

[0086] where P pred represents the consumable consumption prediction value of the hemodialysis center, n represents the number of consumable types, C i represents the unit consumption of the i-th consumable, M i represents the patient number factor, D i represents the department scale factor, and α i , β i , γ i respectively represent the weight coefficients of each factor.

[0087] In the model calculation, incorporating multiple influencing factors such as consumable types, patient numbers, and department scales, and at the same time using a clustering algorithm to analyze the prediction curve and determine dynamic threshold parameters, enables the prediction model to better adapt to consumable consumption changes in different stages and scenarios, overcoming the limitations of traditional fixed thresholds. This not only provides a scientific basis for the inventory management of hemodialysis centers, reduces operating costs, ensures the stable supply of hemodialysis treatment, but also promotes the continuous development of hemodialysis consumable management towards the direction of intelligence and high efficiency, injecting new vitality into improving the level of medical resource management.

[0088] In one embodiment, extracting multi-point scheduling requirements based on the replenishment plan and integrating cross-regional inventory data and transportation constraints using distributed database technology to obtain a preliminary scheduling plan may include the following steps:

[0089] Step S401, obtaining regional node information in the replenishment plan; the regional node information includes inventory identification codes of multiple geographical locations.

[0090] Step S402, obtaining the timeliness threshold and capacity upper limit in the transportation constraint condition; the transportation constraint condition is associated with the path topology.

[0091] Step S403, extracting cross-regional inventory dynamic indicators according to the inventory identification code, and generating a set of candidate transportation paths based on the inventory dynamic indicators and the timeliness threshold; the candidate transportation path set carries a capacity upper limit and a node load parameter.

[0092] Step S404, using the path scoring algorithm to screen the candidate transport path set, and matching the screened transport paths with the multi-point scheduling requirements to obtain a preliminary scheduling plan with path allocation results; the preliminary scheduling plan includes the inventory transfer quantity and transport batch number of each node.

[0093] Specifically, regional node information is first obtained from the consumables replenishment plan. This information contains inventory identification codes of multiple geographical locations, which are used to locate each inventory node. Subsequently, the timeliness threshold and capacity limit in the transportation constraints are obtained. These constraints are closely related to the path topology and play a role in limiting and guiding the planning of the transportation path. Based on the inventory identification code, the system extracts cross-regional inventory dynamic indicators, and then combines the inventory dynamic indicators and timeliness threshold to generate a set of candidate transportation paths. This set not only contains each candidate path, but also carries capacity limits and node load parameters, providing multi-dimensional data support for subsequent screening. Finally, the system uses the path scoring algorithm to screen the candidate transportation path set, matches the screened transportation paths with multi-point scheduling requirements, and successfully generates a preliminary scheduling plan with path allocation results. The plan records the inventory transfer volume and transportation batch number of each node in detail.

[0094] On the one hand, the data of the entire transportation scheduling process is integrated and analyzed, from inventory node information, transportation constraints to inventory dynamic indicators, ensuring that various factors affecting transportation scheduling are taken into account, greatly improving the rationality and feasibility of the scheduling plan. On the other hand, the path scoring algorithm is used to screen paths, enabling the system to select the optimal plan from numerous candidate paths, not only meeting the multi-point scheduling requirements, but also making full use of transportation resources, effectively reducing transportation costs and improving transportation efficiency. In addition, the generated preliminary scheduling plan details the inventory transfer volume and transportation batch numbers of each node, facilitating subsequent tracking and management of the scheduling process, further optimizing the transportation scheduling of hemodialysis consumables, and providing a strong guarantee for the timely supply of consumables in hemodialysis centers.

[0095] In one embodiment, as Figure 3 shown, matching the patient treatment data in the preliminary scheduling plan to analyze abnormal consumption or scheduling deviation, and obtaining resource allocation adjustment suggestions may include the following steps:

[0096] Step S501, obtain the patient treatment data in the preliminary scheduling plan; the patient treatment data includes the usage duration of the treatment equipment and the consumption of consumables.

[0097] Step S502, calculate according to the patient treatment data using the formula to obtain the equipment utilization deviation coefficient and the abnormal consumable consumption index.

[0098] Step S503, judge the equipment utilization deviation coefficient based on a preset threshold. If it exceeds the preset threshold, obtain the department scheduling record corresponding to the treatment equipment.

[0099] Step S504, generate a dynamic resource allocation matrix according to the department scheduling record and the abnormal consumable consumption index.

[0100] Step S505, input the dynamic resource allocation matrix into the scheduling optimization model to obtain the equipment allocation path and the consumable replenishment list.

[0101] Step S506, update the preliminary scheduling plan according to the equipment allocation path and the consumable replenishment list to generate resource allocation adjustment suggestions.

[0102] First, the system obtains patient treatment data from the preliminary scheduling plan, which covers key information such as the usage duration of treatment equipment and the consumption of consumables. Based on this data, the system calculates using a specific formula to obtain the deviation coefficient of equipment utilization rate and the abnormal consumption index of consumables. Subsequently, the system compares the deviation coefficient of equipment utilization rate with a preset threshold. Once the coefficient exceeds the preset threshold, it immediately obtains the department scheduling records corresponding to the treatment equipment. Then, combining the department scheduling records with the abnormal consumption index of consumables, the system generates a dynamic resource allocation matrix. After that, this matrix is input into the scheduling optimization model. Through the operation and analysis of the model, the equipment allocation path and the consumable replenishment list are obtained. Finally, based on the equipment allocation path and the consumable replenishment list, the system updates the preliminary scheduling plan to generate resource configuration adjustment suggestions.

[0103] By deeply mining and analyzing the patient treatment data, problems existing in the process of equipment utilization and consumable consumption, such as the deviation of equipment utilization rate and the abnormal consumption of consumables, are accurately identified, providing a reliable basis for subsequent resource allocation. The generated dynamic resource allocation matrix comprehensively considers the department scheduling records and the abnormal consumption index of consumables, making the resource allocation more in line with the actual needs. Inputting this matrix into the scheduling optimization model further optimizes the equipment allocation path and the consumable replenishment plan, improving the rationality and efficiency of resource configuration. It not only reduces the waste of medical resources but also ensures the smooth progress of hemodialysis treatment, improves the overall operation and management level of the hemodialysis center, and promotes the development of the intelligent and refined allocation of hemodialysis consumable resources.

[0104] In one embodiment, inputting the data in the adjustment suggestions into an inventory prediction model to obtain the dynamic replenishment strategy table for the next cycle may include the following steps:

[0105] Step S601, obtain the characteristic adjustment parameters and historical inventory data in the adjustment suggestions; the historical inventory data contains the inventory change records of multiple cycles.

[0106] Step S602, perform weight allocation on the historical inventory data according to the characteristic adjustment parameters to obtain the adjusted input feature vector.

[0107] Step S603, input the input feature vector into the trained inventory prediction model to obtain a multi-dimensional prediction result; the multi-dimensional prediction result contains the inventory consumption rate and the replenishment demand interval.

[0108] Step S604, analyze the upper and lower limits of the inventory threshold of the target warehouse according to the replenishment demand interval and match them with the current inventory data to obtain the dynamic replenishment strategy table for the next cycle; the upper and lower limits of the inventory threshold correspond to the storage conditions of different categories of goods.

[0109] First, the system obtains the feature adjustment parameters in the resource configuration adjustment suggestion and collects historical inventory data simultaneously. Based on the feature adjustment parameters, the system assigns weights to the historical inventory data, giving different data corresponding importance levels, and then obtains the adjusted input feature vector. Subsequently, this vector is input into the trained and mature inventory prediction model, and through the deep operation of the model, a multi-dimensional prediction result including the inventory consumption rate and the replenishment demand interval is generated. Finally, according to the replenishment demand interval, the system analyzes the upper and lower limits of the inventory thresholds for different item categories in the target warehouse and matches them with the current inventory data to generate a dynamic replenishment strategy table for the next cycle. Each threshold setting in the table strictly corresponds to the storage conditions of different item categories.

[0110] By introducing feature adjustment parameters to assign weights to historical inventory data, the dynamic changes in resource configuration are fully considered, making the input feature vector more targeted and greatly improving the accuracy and adaptability of the inventory prediction model. The multi-dimensional prediction result not only clarifies the inventory consumption rate but also gives the replenishment demand interval, providing a clear direction for accurate replenishment. Determining the upper and lower limits of the inventory threshold in combination with the storage conditions of item categories ensures that inventory management meets both clinical needs and warehousing requirements. The generation of the dynamic replenishment strategy table provides scientific and systematic replenishment guidance for the hemodialysis center, effectively avoiding the risks of inventory backlog or out-of-stock, reducing operating costs, and improving the refinement and intelligence level of hemodialysis consumable inventory management.

[0111] In one embodiment, as Figure 4 shown, the present application also provides a hemodialysis consumable inventory management and allocation device, which may include:

[0112] A data processing module 701, configured to obtain patients' historical treatment data and consumable usage records; use time series analysis algorithms to process the historical treatment data and consumable usage records to obtain the consumable consumption prediction values of each hemodialysis center.

[0113] A solution generation module 702, configured to generate a predicted inventory based on the consumable consumption prediction value and the current inventory data and make a judgment. If the predicted inventory is lower than the preset threshold, trigger a dynamic adjustment mechanism to generate a consumable replenishment plan; is also used to extract multi-point scheduling requirements based on the replenishment plan and use distributed database technology to integrate cross-regional inventory data and transportation constraint conditions to obtain a preliminary scheduling plan.

[0114] A replenishment transfer module 703, configured to match the abnormal consumption or scheduling deviation by analyzing the patients' treatment data according to the preliminary scheduling plan to obtain a resource configuration adjustment suggestion; is also used to input the data in the adjustment suggestion into the inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to judge whether there is a shortage risk for a certain type of consumable. If so, allocate it to high-demand centers according to the treatment safety priority to generate a hierarchical management execution plan.

[0115] The above-mentioned hemodialysis consumable inventory management and allocation device is composed of a data processing module, a solution generation module, and a replenishment mobilization module. The data processing module obtains the patient's historical treatment data and consumable usage records, and processes them using a time series analysis algorithm to obtain the consumable consumption prediction values of each hemodialysis center. The solution generation module generates a predicted inventory based on the consumable consumption prediction value and the current inventory data and makes a judgment. If the predicted inventory is lower than the preset threshold, it triggers a dynamic adjustment mechanism to generate a consumable replenishment plan; it also extracts multi-point scheduling requirements based on the replenishment plan, integrates cross-regional inventory data and transportation constraints using distributed database technology, and obtains a preliminary scheduling plan. The replenishment mobilization module matches the patient treatment data according to the preliminary scheduling plan, analyzes abnormal consumption or scheduling deviation, and obtains resource allocation adjustment suggestions; it inputs the data in the adjustment suggestions into an inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle. This table is used to judge whether there is a shortage risk for a certain type of consumable. If there is, it is allocated to high-demand centers according to the treatment safety priority, and finally a hierarchical management execution plan is generated. It greatly improves the efficiency of cross-regional resource allocation and further optimizes resource allocation. It can not only accurately judge the shortage risk of consumables, but also allocate them according to the treatment safety priority, ensuring that resource allocation is tilted towards high-demand centers, improving the utilization efficiency of overall medical resources, and facilitating the refined and intelligent transformation of hemodialysis center management.

[0116] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0117] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned method, device, equipment, and medium for managing and allocating hemodialysis consumable inventory.

[0118] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the above-mentioned method embodiments.

[0119] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0120] The above embodiments only represent several implementation manners of the embodiments of the present application. The descriptions are relatively specific and detailed, but they should not be construed as a limitation on the scope of the patents of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A method for inventory management and allocation of hemodialysis consumables, characterized in that, The method includes: Obtaining the patient's historical treatment data and consumable usage records; processing the historical treatment data and consumable usage records using a time series analysis algorithm to obtain the predicted consumable consumption values for each hemodialysis center; Generating a predicted inventory based on the predicted consumable consumption values and the current inventory data and making a judgment. If the predicted inventory is lower than a preset threshold, a dynamic adjustment mechanism is triggered to generate a consumable replenishment plan; Extracting multi-point scheduling requirements based on the replenishment plan and using distributed database technology to integrate cross-regional inventory data and transportation constraints to obtain a preliminary scheduling plan; Matching the preliminary scheduling plan with the patient treatment data to analyze abnormal consumption or scheduling deviation to obtain resource allocation adjustment suggestions; Inputting the data in the adjustment suggestions into an inventory prediction model to obtain a dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to judge whether there is a shortage risk for a certain type of consumable. If there is, it is allocated to high-demand centers according to the treatment safety priority to generate a hierarchical management implementation plan.

2. The method according to claim 1, wherein The processing of the historical treatment data and consumable usage records using a time series analysis algorithm to obtain the predicted consumable consumption values for each hemodialysis center includes: Extracting the historical treatment data and consumable usage records to obtain a consumable consumption time series; Using a time series analysis algorithm to perform periodic decomposition on the consumable consumption time series to obtain a trend term, a seasonal term, and a residual term; Constructing a consumable consumption prediction model based on the trend term and the seasonal term to obtain the predicted consumable consumption values for each hemodialysis center; Obtaining the fluctuation range of the residual term and judging whether the residual term exceeds a preset fluctuation threshold; if the residual term exceeds the fluctuation threshold, it is marked as an abnormal consumption event; Associating the abnormal consumption event with the corresponding hemodialysis center number and treatment parameters to obtain a list of abnormal consumption events; Adjusting the parameters of the consumable consumption prediction model based on the list of abnormal consumption events to obtain the predicted consumable consumption values for each hemodialysis center.

3. The method according to claim 2, wherein The constructing a consumable consumption prediction model based on the trend term and the seasonal term to obtain the predicted consumable consumption values for each hemodialysis center includes: Associating and matching the trend term with the equipment maintenance records of the hemodialysis center. If the slope of the trend term changes after the maintenance time, a consumable consumption rate correction instruction is triggered; Adjusting the cycle parameters of the seasonal term according to the correction instruction to generate an updated consumable consumption prediction curve; Performing clustering analysis on the prediction curve using a clustering algorithm to divide it into different data clusters, and obtaining dynamic threshold parameters according to the boundary characteristics of the remaining clusters; Inputting the dynamic threshold parameters into the consumable consumption prediction model and calculating the predicted consumable consumption values for each hemodialysis center using a formula.

4. The method according to claim 3, wherein The predicted consumable consumption values are calculated through the following formula: Among them, P pred represents the predicted value of the consumable consumption in the hemodialysis center, n represents the number of consumable types, C i represents the unit consumption of the i-th consumable, M i represents the patient number factor, D i represents the department scale factor, α i , β i , γ i respectively represent the weight coefficients of each factor.

5. The method according to claim 1, characterized in that, The extracting multi-point scheduling requirements based on the replenishment plan and using distributed database technology to integrate cross-regional inventory data and transportation constraints to obtain a preliminary scheduling plan includes: Obtaining the regional node information in the replenishment plan; the regional node information includes inventory identification codes of multiple geographical locations; Acquire the timeliness threshold and the capacity upper limit in the transport constraint condition; the transport constraint condition is associated with the path topology; Extracting cross-regional inventory dynamic indicators according to the inventory identification code, and generating a set of candidate transportation paths based on the inventory dynamic indicators and the timeliness threshold; the set of candidate transportation paths carries a capacity upper limit and a node load parameter; The candidate transport path set is screened using a path scoring algorithm, and the screened transport paths are matched with the multi-point scheduling requirements to obtain a preliminary scheduling plan with path allocation results; the preliminary scheduling plan includes the inventory transfer quantity and transport batch number of each node.

6. The method according to claim 1, characterized in that, The matching of the patient treatment data with the preliminary scheduling plan to analyze abnormal consumption or scheduling deviation and obtain resource allocation adjustment suggestions includes: Acquire the patient treatment data in the preliminary scheduling plan; the patient treatment data includes the use time of treatment equipment and the consumption of consumables; Calculate the equipment utilization rate deviation coefficient and the consumables abnormal consumption index using a formula according to the patient treatment data; The equipment utilization rate deviation coefficient is judged based on a preset threshold value, and if it exceeds the preset threshold value, the department scheduling record corresponding to the treatment equipment is obtained; Generate a dynamic resource allocation matrix according to the department scheduling record and the abnormal consumption index of consumables; Input the dynamic resource allocation matrix into the scheduling optimization model to obtain the equipment deployment path and consumables replenishment list; The preliminary scheduling plan is updated according to the equipment deployment path and the consumables replenishment list to generate resource configuration adjustment suggestions.

7. The method according to claim 5, wherein The step of inputting the data in the adjustment suggestion into the inventory forecasting model to obtain a dynamic replenishment strategy table for the next cycle includes: Acquire characteristic adjustment parameters and historical inventory data in the adjustment suggestion; the historical inventory data includes inventory change records of multiple periods; Performing weight distribution on the historical inventory data according to the feature adjustment parameter to obtain an adjusted input feature vector; Inputting the input feature vector into a trained inventory forecasting model to obtain a multi-dimensional forecasting result; the multi-dimensional forecasting result includes an inventory consumption rate and a replenishment demand interval; The upper and lower limits of the inventory threshold of the target warehouse are analyzed according to the replenishment demand interval and matched with the current inventory data to obtain a dynamic replenishment strategy table for the next cycle; the upper and lower limits of the inventory threshold correspond to the storage conditions of different categories of goods.

8. A hemodialysis consumable inventory management and allocation device, characterized in that, The device comprises: A data processing module is used to obtain the patient's historical treatment data and consumables usage records; use a time series analysis algorithm to process the historical treatment data and consumables usage records to obtain the consumables consumption forecast value of each hemodialysis center; A plan generation module is used to generate a forecast inventory based on the predicted value of consumable consumption and the current inventory data and make a judgment. If the predicted inventory is lower than a preset threshold, a dynamic adjustment mechanism is triggered to generate a consumable replenishment plan; it is also used to extract multi-point scheduling requirements based on the replenishment plan and use distributed database technology to integrate cross-regional inventory data and transportation constraints to obtain a preliminary scheduling plan; The replenishment transfer module is used to match abnormal consumption or scheduling deviation based on the preliminary scheduling plan for patient treatment data analysis, and obtain resource allocation adjustment suggestions; it is also used to input the data in the adjustment suggestions into an inventory forecasting model to obtain a dynamic replenishment strategy table for the next cycle; the dynamic replenishment strategy table is used to determine whether there is a shortage risk for a certain type of consumable. If there is, it is allocated to high-demand centers according to the treatment safety priority to generate a hierarchical management implementation plan.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images