A big data-based disposable tableware packaging intelligent management method and system

Abstract

The application discloses a one-off tableware packaging intelligent management method and system based on big data, belongs to the technical field of intelligent medical treatment and logistics management, and comprises the following steps: S1, inherent risk factors and controllable risk factors of a management unit are collected, and historical consumption data of the management unit is collected; S2, based on the inherent risk factors and the controllable risk factors, a quantified ward total risk score is calculated and generated; S3, based on the ward total risk score and the historical consumption data, a dynamic optimal reserve quantity of one-off tableware packaging is calculated and generated; S4, current actual inventory of the management unit is acquired, and the current actual inventory is compared with the dynamic optimal reserve quantity; and S5, if the current actual inventory is lower than the dynamic optimal reserve quantity, a replenishment task is generated; and if the current actual inventory is not lower than the dynamic optimal reserve quantity, the step S4 is returned to be executed. The application lays a foundation for realizing predictive and risk-driven management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent medical treatment and logistics management, in particular to a disposable tableware packaging intelligent management method and system based on big data. BACKGROUND

[0002] In response to public health emergencies, the operation and management of hospital isolation wards face severe challenges. Disposable tableware, as a key material to ensure basic living needs and prevent cross-infection, its supply management is the core link of infection control. Existing technologies, such as regular and quantitative distribution, on-demand requisition or excessive reserve in the ward, can operate under normal conditions, but when the ward function, the number of patients and the risk level change rapidly in a sudden event, these modes expose their inherent technical defects. Specifically, they cannot solve the exponential coupling effect caused by the infection prevention and control safety level and the response speed of tableware supply under the influence of public health emergencies, resulting in an unexpected technical contradiction between safety and timeliness, which constitutes a technical problem to be solved in the current emergency medical material management field.

[0003] The above information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, therefore it can include information which does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0004] The purpose of the present application is to provide a disposable tableware packaging intelligent management method and system based on big data to solve the problems raised in the above background.

[0005] The technical solution of the present application is a disposable tableware packaging intelligent management method based on big data, comprising the following steps:

[0006] S1, collecting the inherent risk factors and controllable risk factors of the management unit, and collecting the historical consumption data of the management unit;

[0007] S2, based on the inherent risk factors and controllable risk factors, calculating and generating a quantitative ward total risk score;

[0008] S3, based on the ward total risk score and the historical consumption data, calculating and generating a dynamic optimal reserve amount of disposable tableware packaging;

[0009] S4, obtaining the current actual inventory of the management unit, and comparing the current actual inventory with the dynamic optimal reserve amount;

[0010] S5, if the current actual inventory is lower than the dynamic optimal reserve amount, a replenishment task is generated; if the current actual inventory is not lower than the dynamic optimal reserve amount, return to step S4;

[0011] S6, in response to the replenishment task, based on the total risk score of the ward, calculating and planning a distribution path with minimum overall risk cost, and issuing a distribution path instruction.

[0012] Preferably, S2 specifically comprises:

[0013] S21, setting weight coefficients corresponding to the inherent risk factor and the controllable risk factor respectively;

[0014] S22, weighted sum of the inherent risk factor and the controllable risk factor to generate the total risk score of the ward.

[0015] Preferably, S3 specifically comprises:

[0016] S31, calculating the deterministic demand part based on historical consumption data;

[0017] S32, taking the total risk score of the ward as an adjustment coefficient to calculate the risk adaptive safety stock part;

[0018] S33, summing the deterministic demand part and the risk adaptive safety stock part to generate the dynamic optimal reserve amount.

[0019] Preferably, S6 specifically comprises:

[0020] S61, calculating the environmental risk rating of each road segment in the hospital topology graph according to the total risk score of the ward;

[0021] S62, calculating the path risk cost of the road segment based on the environmental risk rating and the estimated travel time of the road segment;

[0022] S63, using a path planning algorithm to solve the distribution path by taking the path risk cost as the weight of each edge in the graph.

[0023] Preferably, the inherent risk factor is a low-frequency update parameter set according to the expert knowledge base of the infection control department; the controllable risk factor is a high-frequency update dynamic parameter obtained according to real-time sensor data.

[0024] Preferably, the calculation of the risk adaptive safety stock part is also based on a preset risk sensitivity coefficient; the risk sensitivity coefficient is a adjustable strategy parameter set by the hospital management according to the emergency response level and the material adequacy.

[0025] Preferably, the calculation of the path risk cost is also based on a preset time risk preference coefficient; the time risk preference coefficient is used to balance the weight of timeliness and safety in path planning.

[0026] A disposable tableware packaging intelligent management system based on big data, comprising:

[0027] A data collection module is configured to collect inherent risk factors, controllable risk factors and historical consumption data of the management unit;

[0028] A risk score module is configured to calculate and generate a quantitative ward total risk score based on the inherent risk factors and the controllable risk factors;

[0029] A reserve calculation module is configured to calculate and generate a dynamic optimal reserve amount of the disposable tableware packaging based on the ward total risk score and the historical consumption data;

[0030] An inventory monitoring module is configured to compare the current actual inventory with the dynamic optimal reserve amount, and generate a replenishment task when the current actual inventory is lower than the dynamic optimal reserve amount;

[0031] A path planning module is configured to calculate and plan a distribution path with minimized total risk cost based on the ward total risk score in response to the replenishment task, and issue a distribution path instruction.

[0032] The present application provides an intelligent management method and system for disposable tableware packaging based on big data, which has the following improvements and advantages compared with the prior art:

[0033] 1. The present application realizes dynamic quantification and accurate perception of nosocomial infection risk. By collecting inherent risk factors and controllable risk factors of the management unit and applying a ward total risk score model, the abstract risk is converted into a precise and dynamically updated quantitative index. By combining stable basic risk with immediate environmental changes, a ward total risk score that can be used as a unified decision basis for the whole system is generated. This scoring mechanism enables managers to first understand the risk distribution and its dynamic evolution throughout the hospital in a data-driven manner, laying the foundation for predictive and risk-driven management;

[0034] 2. The present application establishes a risk-adaptive dynamic optimal reserve strategy, so that the safety inventory level is no longer only a function of demand fluctuations, but also a direct function of risk level. When a certain isolation ward has an increase in controllable risk factors due to the admission of critically ill patients, the ward total risk score calculated by the system will increase, and the dynamic optimal reserve amount of disposable tableware packaging for the ward will be automatically adjusted, so that the material buffer is completed in advance before the risk actually evolves into a supply interruption, reducing the risk of tableware supply interruption in high-risk wards and shortening the supply response time;

[0035] 3.The intelligent distribution path of the present application minimizes the overall risk cost, and the present application calculates and plans the distribution path based on the ward total risk score through the path risk cost model when responding to the replenishment task; a new cost measurement, i.e., risk equivalent time, is defined, which quantifies and unifies the intangible infection risk and the tangible time cost; the path planning algorithm takes this as the weight for solving, and the result is no longer the shortest path in the traditional sense, but a path with the lowest comprehensive exposure risk; when a distribution task needs to pass through the corridor of a high-risk ward door, even if the path is the shortest, the system will give it a very high path risk cost because of the high environmental risk rating of the section, and thus actively plan an alternative path that bypasses the low-risk area; this design deeply integrates the infection control strategy into logistics execution, making every material transportation a proactive risk avoidance behavior. BRIEF DESCRIPTION OF DRAWINGS

[0036] The present application will be further explained in conjunction with the accompanying drawings and embodiments:

[0037] Figure 1 is a flow chart of a disposable tableware packaging intelligent management method based on big data. DETAILED DESCRIPTION

[0038] To make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in conjunction with specific embodiments.

[0039] Embodiment 1:

[0040] Please refer to Figure 1 The present application provides a disposable tableware packaging intelligent management method based on big data, which comprises the following steps: S1, collecting the inherent risk factors and controllable risk factors of the management unit, and collecting the historical consumption data of the management unit;

[0041] S2, calculating and generating the quantified ward total risk score based on the inherent risk factors and controllable risk factors;

[0042] S3, calculating and generating the dynamic optimal reserve quantity of disposable tableware packaging based on the ward total risk score and the historical consumption data;

[0043] S4, obtaining the current actual inventory of the management unit, and comparing the current actual inventory with the dynamic optimal reserve quantity;

[0044] S5, if the current actual inventory is lower than the dynamic optimal reserve quantity, a replenishment task is generated; if the current actual inventory is not lower than the dynamic optimal reserve quantity, return to step S4;

[0045] S6, in response to the replenishment task, based on the ward total risk score, calculating and planning a distribution path with minimum overall risk cost, and issuing a distribution path instruction.

[0046] The one-off tableware packaging intelligent management method based on big data provided by the embodiment establishes a complete operation process integrating data collection, risk quantification, dynamic reserve calculation, inventory monitoring, task generation and path intelligent planning; the method realizes automatic closed-loop control from risk perception to material response by directly linking the risk assessment result with inventory and logistics decision; the fundamental purpose is to unify the originally conflicting safety and timeliness targets into a calculable and optimal framework through a data-driven actuarial model, thereby maximizing the efficiency and reliability of material supply and reducing the overall operating cost on the premise of guaranteeing infection control requirements.

[0047] Embodiment 2

[0048] S2 specifically includes:

[0049] S21, setting weight coefficients corresponding to the inherent risk factor and the controllable risk factor respectively;

[0050] S22, weighted sum of the inherent risk factor and the controllable risk factor to generate a ward total risk score;

[0051] The inherent risk factor is a low-frequency update parameter set according to the expert knowledge base of the hospital infection department; the controllable risk factor is a high-frequency update dynamic parameter obtained according to real-time sensor data.

[0052] In the present embodiment, the calculation of the ward total risk score aims to convert the complex nosocomial infection risk into a standardized quantitative index; to achieve this purpose, the ward total risk score model is introduced in this step, and the internal logic is to decompose the risk into two dimensions of relatively stable inherent risk and real-time variable controllable risk, and through dynamic weighted sum, it can accurately reflect the comprehensive risk level at a specific time point; the mathematical expression of the model is: ; in the formula, represents a management unit at time The dimensionless total risk score at time is the unique identifier of the management unit, is the time stamp; is the inherent risk factor of the management unit , which is a low-frequency update parameter, and its value is set according to the static information about the physical layout of the ward, the basic isolation conditions, etc. in the expert knowledge base of the hospital infection department;

[0053] This value can be quantified by a score table; for example, for each management unit Score and sum according to the following rules:

[0054] Ward type: single isolation room 0 points; double room 5 points; multi-person room 10 points;

[0055] Isolation facility: equipped with negative pressure ventilation system 0 points; with independent anteroom but without negative pressure ventilation 3 points; without independent anteroom or effective isolation facility 5 points;

[0056] Regional location: located in the independent infection floor of the hospital 0 points; located in the isolation end area of the general floor 2 points; mixed with other general wards or on the main trunk of human flow 5 points;

[0057] That is, the sum of the scores of the above items, and can be normalized as needed;

[0058] Management unit At the moment Controllable risk factor, this is a high-frequency updated dynamic parameter, the value comes from real-time sensor network collected data such as patient density, medical staff flow frequency, ventilation system efficiency, etc.

[0059] This value can be generated by normalizing and weighted summing of each sensor data; the original readings of each sensor are mapped to interval by a max-min normalization function , where and are preset safety thresholds or historical extreme values; the following formula can be used for calculation:

[0060]

[0061] In the formula, is the real-time patient density, is the medical staff flow frequency, is the ventilation system efficiency; are the corresponding weight coefficients, respectively, satisfying The value can be set by hospital infection experts according to the contribution of different factors to the risk of infection; please note that the coefficient before the ventilation efficiency is negative, indicating that the higher the ventilation efficiency, the lower the risk;

[0062] and are the top-level weight coefficients corresponding to the inherent and controllable risk factors, respectively, both of which are dimensionless parameters and satisfy The setting can be adjusted by the hospital management according to the emergency response level, or optimized through regression analysis of historical infection event data; : raw reading of the sensor; : preset safety threshold or historical minimum value of the sensor reading; : preset safety threshold or historical maximum value of the sensor reading; : max-min normalization function for mapping the sensor raw reading to interval;

[0063] For example, a logistic regression model can be constructed, with the historical infection event in a specific time window as the dependent variable (1 = yes, 0 = no), and the average of the inherent risk factors and controllable risk factors of the corresponding management unit in the time window as the independent variables, and the coefficients obtained by model fitting to objectively determine the weights of the two.

[0064] This model runs at a preset frequency, for example, every five minutes, and continuously updates the risk score of each management unit based on the latest data input, forming a dynamic risk heat map covering the entire hospital, thereby providing accurate, dynamic and quantifiable input for subsequent material management decisions.

[0065] Embodiment 3

[0066] S3 specifically includes:

[0067] S31, based on historical consumption data, calculating the deterministic demand part;

[0068] S32, taking the total risk score of the ward as the adjustment coefficient, calculating the risk-adaptive safety stock part;

[0069] S33, summing the deterministic demand part and the risk-adaptive safety stock part to generate the dynamic optimal reserve;

[0070] The calculation of the risk-adaptive safety stock part is also based on a preset risk sensitivity coefficient; the risk sensitivity coefficient is a adjustable strategy parameter set by the hospital management according to the emergency response level and the material adequacy;

[0071] In this embodiment, the calculation of the dynamic optimal reserve is realized through an inventory model that introduces a risk adjustment factor; the technical motivation of this model is that traditional inventory theory only focuses on the uncertainty of demand, without considering that in a high-risk environment, the possibility of supply disruption and its consequences will increase sharply; therefore, based on the classical inventory model, this scheme takes the total risk score calculated in the previous step as a key adjustment variable to dynamically adjust the safety stock level; the mathematical expression is: ; the logical structure of this formula consists of two parts: the first part is the average consumption within the lead time that meets the deterministic demand; the second part is the risk adaptive safety stock defined by the present invention; wherein, represents a management unit is for the optimal reserve quantity of the type of tableware, whose physical dimension is quantity; is the historical daily consumption quantity, whose unit is quantity / day; is the average replenishment lead time, whose unit is day; is the standard deviation of daily consumption quantity, whose unit is quantity / day; directly quotes the result from the aforementioned risk score model; is a dimensionless risk sensitivity coefficient, which is an adjustable strategy parameter, set by the hospital management according to the emergency response level and the material abundance, for example, when the material is abundant in the daily state, a lower risk sensitivity can be set, such as ; when entering the early warning period of a specific infectious disease or when the material is in short supply, the coefficient can be increased to or higher, these values are only examples, and the specific values can be calibrated by the hospital according to the actual situation; the dimensions of the two terms on the right side of the formula are (quantity / day) x (day), and the result is quantity, which is consistent with the dimension on the left side; the application effect of this model is that when the risk score of a certain management unit increases, even if its historical demand fluctuation remains unchanged, the system will actively increase its safety stock level, thereby foreseeably hedging against supply disruptions that may be caused by a high-risk environment, ensuring the continuity of the supply of critical materials; : the type of disposable tableware.

[0072] Embodiment 4

[0073] S6 specifically includes:

[0074] S61, according to the total risk score of the ward, calculate the environmental risk rating of each road segment in the hospital topology graph;

[0075] S62, based on the environmental risk rating and the estimated travel time of the road segment, calculate the path risk cost of the road segment;

[0076] S63, use the path planning algorithm, take the path risk cost as the weight of each edge in the graph, and solve the distribution path;

[0077] The calculation of the path risk cost is also based on a preset time risk preference coefficient; the time risk preference coefficient is used to balance the weight of timeliness and safety in path planning.

[0078] In order to make the setting of this parameter more standardized, a recommended value can be preset in connection with the hospital emergency response level, for example:

[0079] Daily state, first-level response: high safety requirement, time efficiency second, can be set , i.e. 70% weight of path cost is given to risk.

[0080] Emergency state, third-level response: time efficiency first, need to be delivered as soon as possible, can be set , i.e. 80% weight of path cost is given to time;

[0081] General state, second-level response: both safety and time efficiency are considered, can be set ;

[0082] In this embodiment, the delivery path planning with minimum overall risk cost aims to calculate a path that can achieve the optimal balance between time efficiency and safety; the technical motivation is that traditional path planning algorithms take time or distance as the only optimization target, which has significant defects in the hospital environment that needs to strictly control the risk of infection; this scheme designs a new cost function, which takes the environmental exposure risk of the path into account and performs weighted summation with the time cost; the overall risk cost model of the path is mathematically expressed as: ; wherein, represents the overall risk cost of the complete delivery path , the physical dimension of which is second, which can be understood as risk equivalent time; is a path composed of multiple road segments ; is an edge in the hospital topology map, such as a corridor or an elevator; is the estimated travel time through road segment , in seconds; is the dimensionless environmental risk rating of road segment , which is obtained by spatially weighted averaging of the total risk score of all management units adjacent to the road segment, representing the exposure risk level through the road segment;

[0083] The spatially weighted average can be calculated using the inverse distance weighting method; for any road segment in the map, the environmental risk rating is calculated as follows:

[0084]

[0085] wherein, is the management unit adjacent to road segment in the topology map, is the total number of all adjacent management units; is the Euclidean distance from the geometric center of road segment to the center of management unit ; is the management unit At any moment Overall risk score; It is a power exponent, usually with a value of 2. p=2 means that the influence of distance decreases inversely with the square. This is a classic model widely used in spatial interpolation, which can effectively reflect the dominant role of the risk of the nearest neighbor unit. It means that the greater the distance, the lower the weight of the risk score inversely with the square.

[0086] The time-risk preference coefficient is a dimensionless coefficient that takes values ​​in the interval [0, 1], used to balance the weights of timeliness and safety in route planning; all terms on the right side of the formula are in seconds to ensure dimensional consistency; when responding to delivery tasks, the system uses the latest... Update each edge in the graph of , and then in this way The formula serves as the weight of edges in path planning algorithms such as A* or Dijkstra's algorithm, solving for the optimal path that minimizes overall risk cost. This method ensures that the delivery process proactively avoids high-risk areas, materializing infection control strategies into every aspect of logistics.

[0087] Example 5

[0088] A big data-based intelligent management system for disposable tableware packaging includes: a data acquisition module for collecting inherent risk factors, controllable risk factors, and historical consumption data of the management unit;

[0089] The risk scoring module is used to calculate and generate a quantitative total risk score for the ward based on inherent risk factors and controllable risk factors.

[0090] The reserve calculation module is used to calculate and generate the dynamic optimal reserve quantity of disposable tableware packaging based on the total risk score of the ward and historical consumption data.

[0091] The inventory monitoring module is used to obtain the current actual inventory, compare it with the dynamic optimal reserve level, and generate a replenishment task when the current actual inventory is lower than the dynamic optimal reserve level.

[0092] The route planning module is used to respond to replenishment tasks, calculate and plan the delivery route that minimizes the overall risk cost based on the total risk score of the ward, and issue delivery route instructions.

[0093] The application also provides an intelligent management system for realizing the above method; the system is composed of a series of functionally independent hardware or software modules, which work together to realize the complete closed-loop management function; the system specifically comprises: a data acquisition module as the input interface of the system, responsible for continuously collecting multi-source data from the hospital infection expert knowledge base, real-time sensor network and historical order database; a risk score module as the core analysis unit of the system, which internally executes the aforementioned ward total risk score model to convert the original data into a quantitative risk score; a reserve calculation module, which receives the output of the risk score module and runs the aforementioned dynamic optimal reserve model to generate dynamic inventory suggestions for each material of the management unit; an inventory monitoring module, responsible for real-time monitoring of the actual inventory of each management unit, and comparing with the dynamic optimal reserve quantity generated by the reserve calculation module, when the actual inventory is lower than the reserve quantity, automatically generating a replenishment task; and a path planning module, which immediately calls the aforementioned overall risk cost model after receiving the replenishment task, combines the latest risk data to calculate and plan the optimal distribution path, and then issues the path instructions to the distribution personnel or automated logistics equipment; through the organic integration and seamless cooperation of these modules, the whole system can adaptively respond to the changes of environmental risks and material demands, so as to realize the efficient, accurate and safe management of emergency materials.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A big data-based disposable tableware package intelligent management method, characterized in that: The method comprises the following steps: S1, collecting inherent risk factors and controllable risk factors of a management unit, and collecting historical consumption data of the management unit; S2, calculating a quantified ward total risk score based on the inherent risk factors and the controllable risk factors; S3, calculating a dynamic optimal reserve amount of disposable tableware packaging based on the ward total risk score and the historical consumption data; S4, obtaining a current actual inventory of the management unit, and comparing the current actual inventory with the dynamic optimal reserve amount; S5, if the current actual inventory is lower than the dynamic optimal reserve amount, a replenishment task is generated; if the current actual inventory is not lower than the dynamic optimal reserve amount, returning to step S4; S6, in response to the replenishment task, calculating and planning a delivery path with a minimum overall risk cost based on the ward total risk score, and issuing a delivery path instruction; S6 specifically comprises: S61, calculating an environmental risk rating of each road section in a hospital topology diagram according to the ward total risk score; S62, calculating a path risk cost of the road section based on the environmental risk rating and an estimated travel time of the road section; S63, using a path planning algorithm to solve the delivery path by taking the path risk cost as the weight of each edge in the diagram; The calculation of the path risk cost is also based on a preset time risk preference coefficient; the time risk preference coefficient is used to balance the weight of timeliness and safety in path planning; The overall risk cost model of a path is mathematically expressed as: ; wherein, represents the overall risk cost of a complete delivery path , whose physical dimension is second; is a path composed of multiple road segments ; is an edge in the hospital topology graph; is the estimated travel time through road segment , in seconds; is the dimensionless environmental risk rating of road segment ; is the dimensionless time risk preference coefficient, which takes value in the interval [0, 1]. Environmental risk rating The formula for calculating the environmental risk rating is as follows: ； wherein, is a management unit of a neighboring road segment in the topological graph, is the total number of all neighboring management units; is the Euclidean distance from the geometric center point of the road segment to the center point of the management unit ; is the total risk score of the management unit at the time instant ; is a power exponent, which takes the value 2.

2. The big data-based disposable tableware package intelligent management method according to claim 1, characterized in that, S2 specifically comprises: S21, setting weight coefficients corresponding to the inherent risk factors and the controllable risk factors respectively; S22, performing weighted summation on the inherent risk factors and the controllable risk factors to generate the ward total risk score. 3.The big data-based disposable tableware package intelligent management method according to claim 1, wherein, S3 specifically comprises: S31, calculating a deterministic demand part based on the historical consumption data; S32, calculating a risk-adaptive safety stock part by taking the ward total risk score as an adjustment coefficient; S33, summing the deterministic demand part and the risk-adaptive safety stock part to generate the dynamic optimal reserve amount. 4.The big data-based disposable tableware package intelligent management method according to claim 2, wherein, The inherent risk factors are low-frequency update parameters set according to expert knowledge base of the infection control department; the controllable risk factors are high-frequency update dynamic parameters obtained according to real-time sensor data. 5.The big data-based disposable tableware package intelligent management method according to claim 3, wherein, The calculation of the risk-adaptive safety stock part is also based on a preset risk sensitivity coefficient; the risk sensitivity coefficient is a adjustable strategy parameter set by the hospital management according to the emergency response level and the material adequacy.

6. A big data-based disposable tableware packaging intelligent management system based on the big data-based disposable tableware packaging intelligent management method of any one of claims 1 to 5, characterized in that, It comprises: a data collection module for collecting inherent risk factors, controllable risk factors and historical consumption data of a management unit; a risk score module for calculating a quantified ward total risk score based on the inherent risk factors and the controllable risk factors; a reserve calculation module for calculating a dynamic optimal reserve amount of disposable tableware packaging based on the ward total risk score and the historical consumption data; an inventory monitoring module for obtaining a current actual inventory, comparing the current actual inventory with the dynamic optimal reserve amount, and generating a replenishment task when the current actual inventory is lower than the dynamic optimal reserve amount; a path planning module for calculating and planning a delivery path with a minimum overall risk cost based on the ward total risk score in response to the replenishment task, and issuing a delivery path instruction.

Images