A multi-hospital cooperative nursing demand prediction and human resource planning method and system

Abstract

The present application relates to a kind of multi-institutional collaborative nursing needs prediction and manpower planning method and system, belong to nursing strategy optimization field.Therein, the method includes collecting multi-institutional multi-source data and carrying out integration and cleaning, obtain multi-institutional nursing data lake;Dynamic nursing demand evaluation model is constructed based on multi-institutional nursing data lake, obtain dynamic nursing demand index and demand pressure prediction index;Multi-dimensional competence-load matching model is constructed based on multi-institutional nursing data lake, obtain real-time available competence;Based on dynamic nursing demand index, demand pressure prediction index and real-time available competence, multi-institutional collaborative manpower planning model is constructed, the construction of multi-institutional collaborative manpower planning model includes the construction of multi-objective planning utility function and the introduction of dynamic ethical constraint mechanism, dynamic ethical constraint mechanism includes fatigue accumulation constraint and future risk constraint.The present application realizes the combination of multi-institutional data lake and dynamic prediction model, realizes cross-institutional collaborative scheduling.

Description

Technical Field

[0001] This invention belongs to the field of nursing strategy optimization technology, specifically involving a method and system for predicting nursing needs and coordinating human resources across multiple hospital areas. Background Technology

[0002] Currently, hospital nursing human resource allocation relies heavily on static scheduling tables and experience-based decisions. Common systems such as rule-based scheduling software and electronic schedule systems, while capable of basic staff allocation, have significant shortcomings: First, they lack the ability to dynamically respond to real-time nursing needs, making them unable to handle emergencies such as surges in emergency rooms or staff absenteeism. Second, they fail to comprehensively consider the multidimensional states of nursing staff, leading to inefficient staff allocation and a high risk of staff burnout. Third, cross-hospital collaboration mechanisms are lacking, with each hospital often operating independently, hindering the optimized sharing of human resources and emergency support. Fourth, existing systems primarily focus on cost control, making it difficult to strike a balance between efficiency and humanization. These limitations often result in staff shortages or resource waste when facing complex and ever-changing nursing needs, severely impacting nursing quality and patient safety. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for predicting nursing needs and coordinating human resources across multiple hospital campuses.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A method for collaborative nursing demand forecasting and human resource allocation across multiple hospital campuses, the implementation of which includes the following steps:

[0006] S1: Collect multi-source data from multiple hospital areas, integrate and clean the data to obtain a multi-hospital nursing data lake;

[0007] S2: Based on the multi-hospital nursing data lake, a dynamic nursing demand assessment model is constructed to obtain the dynamic nursing demand index and the demand pressure prediction index;

[0008] S3: Construct a multi-dimensional competency-load matching model based on the multi-hospital nursing data lake to obtain real-time available competencies;

[0009] S4: Based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence, a multi-hospital collaborative human resource management model is constructed. The construction of the multi-hospital collaborative human resource management model includes the construction of a multi-objective overall planning utility function and the introduction of a dynamic ethical constraint mechanism. The dynamic ethical constraint mechanism includes fatigue accumulation constraint and future risk constraint.

[0010] Preferably, the construction of the dynamic nursing needs assessment model in step S2 specifically involves:

[0011] S201: Extract real-time nursing demand features based on the multi-hospital nursing data lake. The real-time nursing demand features include the total number of patients, the proportion of high-risk patients, the total number of nursing operations, real-time infection risk indicators, and the proportion of patients transferred from the emergency department.

[0012] S202: Based on the real-time nursing demand characteristics, the dynamic nursing demand index and the demand pressure prediction index are obtained;

[0013] S203: The dynamic nursing demand assessment model is obtained based on the dynamic nursing demand index and the demand pressure prediction index.

[0014] Preferably, step S202 specifically includes:

[0015] The mathematical description of the dynamic care demand index is... ,in, For the hospital area exist The dynamic nursing needs index at any given moment. For the hospital area exist The percentage of high-risk patients at any given time For a unit of time, the hospital area Total number of nursing procedures For the hospital area exist Total number of patients at any given time For the hospital area exist Real-time infection risk indicators at any given moment. For the hospital area exist The percentage of patients transferred to the emergency room at any given time. , , and As weight, [·] represents Z-Score standardization;

[0016] The acquisition of the demand stress prediction index specifically involves: pre-setting a set of simulated scenarios; acquiring the dynamic nursing demand prediction index under the simulated scenarios; acquiring the standard deviation of the dynamic nursing demand prediction index; and obtaining the demand stress prediction index based on the dynamic nursing demand prediction index and the standard deviation of the dynamic nursing demand prediction index, mathematically described as follows: ,in, For the hospital area exist Demand pressure forecast index at any given time for Simulate scenarios at all times The dynamic nursing demand forecast index under the following conditions for Standard deviation of the dynamic nursing needs forecast index at any given time. [·] represents the expected value. This represents the risk aversion coefficient.

[0017] Preferably, the construction of the multidimensional competence-load matching model in step S3 is as follows:

[0018] Nursing staff competency indicators were extracted based on the multi-hospital nursing data lake. These indicators include skill level, training bonus, cumulative workload, emotional fatigue index, and specialty matching degree.

[0019] The real-time available competence is obtained based on the aforementioned nursing staff competence index, and is mathematically described as follows: ,in, For the hospital area A nurse Real-time availability of competence at all times For the hospital area A nurse's basic competency score is the sum of their standardized skill level and standardized training bonus points. For load sensitivity coefficient, For the hospital area The normalized cumulative workload of a nursing staff member For the hospital area Specialty matching degree of a certain nursing staff For the hospital area The emotional fatigue index of a nursing staff member This represents the fatigue effect coefficient.

[0020] Preferably, the construction of the multi-objective overall utility function in step S4 includes:

[0021] Obtain real-time labor costs and remaining budget within the period;

[0022] Predict and standardize expected nursing quality scores using historical data;

[0023] The multi-objective overall utility function is obtained, and its mathematical description is as follows: ,in, For multi-objective overall utility function, , and As weight, for Time Campus The total real-time available competence of all nursing staff in the country. Number of hospital campuses This refers to the total number of nursing staff in a single hospital ward. for Real-time human resource costs at any given moment for The remaining budget within the time period at any given moment. This represents the standardized expected score for nursing quality. For the hospital area exist The dynamic nursing needs index at any given moment.

[0024] Preferably, the fatigue accumulation constraint in step S4 is specifically: ,in, For nursing staff exist The cumulative fatigue over time, For nursing staff exist The cumulative fatigue over time, Forgetting factor, For nursing staff exist Cumulative workload at any given moment The fatigue bonus from additional tasks. For indicator functions, This is a safety threshold;

[0025] The specific future risk constraints are as follows: ,in, Forward-looking strength coefficient, For the hospital area exist Demand pressure forecast index at any given time.

[0026] A multi-hospital collaborative nursing demand forecasting and human resource coordination system is used to execute the nursing demand forecasting and human resource coordination method described above, including a data processing module, a demand assessment module, a competency assessment module, and a human resource coordination module.

[0027] The data processing module is used to collect multi-source data from multiple hospital areas and integrate and clean it to obtain a multi-hospital nursing data lake.

[0028] The demand assessment module is used to construct a dynamic nursing demand assessment model based on the multi-hospital nursing data lake to obtain a dynamic nursing demand index and a demand pressure prediction index.

[0029] The competency assessment module is used to construct a multidimensional competency-load matching model based on the multi-hospital nursing data lake to obtain real-time available competencies.

[0030] The human resource coordination module is used to construct a multi-hospital collaborative human resource coordination model based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence. The construction of the multi-hospital collaborative human resource coordination model includes the construction of a multi-objective coordination utility function and the introduction of a dynamic ethical constraint mechanism, which includes fatigue accumulation constraints and future risk constraints.

[0031] The beneficial effects of this invention are as follows:

[0032] By constructing a multi-campus nursing data lake and dynamic prediction model, real-time assessment of nursing needs and stress prediction were achieved. At the same time, by introducing a multi-dimensional competency-load matching model, the real-time availability of nursing staff was accurately quantified. Finally, through multi-objective overall optimization and ethical constraints, efficiency, cost, quality and humanistic management were taken into account, significantly improving the collaborative efficiency of nursing resources across campuses, reducing labor costs, enhancing the ability to respond to emergencies, and reducing the accumulation of fatigue and burnout among nursing staff, ultimately achieving a multi-dimensional improvement in nursing quality and patient safety. Attached Figure Description

[0033] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0034] Figure 1 This is a flowchart illustrating the steps of a multi-hospital collaborative nursing demand prediction and human resource coordination method according to the present invention. Detailed Implementation

[0035] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values ​​that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0036] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0037] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0038] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0039] Example 1:

[0040] Please see Figure 1 A collaborative method for predicting nursing needs and coordinating human resources across multiple hospital campuses, comprising:

[0041] S1: Collect multi-source data from multiple hospital areas, integrate and clean the data to obtain a multi-hospital nursing data lake;

[0042] The multi-source data from various hospital areas is obtained by collecting data in real time from electronic health records (which can obtain patient diagnosis, severity of illness, medical orders, nursing plans, etc.), nursing management information systems (which can obtain nurse schedules, on-duty status, nursing activities being performed, etc.), IoT devices (such as smart mattresses, wristbands, etc.), and hospital operation systems (which can obtain the number of people queuing for emergency admission, the number of expected discharges, etc.). The data is then processed to remove duplicates, missing values, and outliers, and the timestamps, units, and coding standards are standardized to form a unified, real-time updatable nursing data lake for the various hospital areas.

[0043] S2: Based on the multi-hospital nursing data lake, a dynamic nursing demand assessment model is constructed to obtain the dynamic nursing demand index and the demand pressure prediction index;

[0044] S3: Based on the multi-hospital nursing data lake, construct a multi-dimensional competency-load matching model for nursing staff to obtain real-time available competencies;

[0045] S4: Based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence, a multi-hospital collaborative human resource management model is constructed. The construction of the multi-hospital collaborative human resource management model includes the construction of a multi-objective overall planning utility function and the introduction of a dynamic ethical constraint mechanism. The dynamic ethical constraint mechanism includes fatigue accumulation constraint and future risk constraint.

[0046] In this embodiment, the construction of the dynamic nursing needs assessment model is specifically as follows:

[0047] S201: Based on the multi-hospital nursing data lake, extract the real-time nursing demand features of each hospital. The real-time nursing demand features include the total number of patients, the proportion of high-risk patients, the total number of nursing operations, real-time infection risk indicators, and the proportion of patients transferred from the emergency department.

[0048] S202: Based on the real-time nursing demand characteristics, the dynamic nursing demand index and the demand pressure prediction index are obtained;

[0049] S203: Based on the dynamic nursing demand index and the demand pressure prediction index, the dynamic nursing demand assessment model is obtained, the nursing demand of the hospital area is assessed and predicted in real time, and subsequent human resource coordination is carried out according to the current demand (i.e., the dynamic nursing demand index) and the predicted demand (i.e., the demand pressure prediction index).

[0050] In this embodiment, the dynamic nursing demand index and the demand pressure prediction index are obtained based on the real-time nursing demand characteristics, which can be implemented through the following steps:

[0051] S202-1: The mathematical description of the dynamic nursing demand index is... ,in, For the hospital area exist The dynamic nursing needs index at any given moment. For the hospital area exist The percentage of high-risk patients at any given time For a unit of time, the hospital area Total number of nursing procedures For the hospital area exist Total number of patients at any given time For the hospital area exist Real-time infection risk indicators at any given time (a composite indicator, weighted by catheter usage rate, proportion of isolated patients, antibiotic usage rate, etc.) For the hospital area exist The percentage of patients transferred to the emergency room at any given time. , , and As weight, [·] represents Z-Score standardization;

[0052] S202-2: The acquisition of the demand pressure prediction index specifically involves: pre-setting a set of simulated scenarios (such as the emergency department receiving three seriously injured patients in batches and sending them to the ICU, a nurse in a certain ward suddenly feeling unwell and leaving her post, a major accident leading to an increase in surgical procedures, etc.); acquiring the dynamic nursing demand prediction index of the dynamic nursing demand index under specific simulated scenarios (i.e., predicting the dynamic nursing demand index under different simulated scenarios). (Value after time step); obtain the standard deviation of the dynamic nursing demand prediction index under different simulation scenarios; based on the dynamic nursing demand prediction index and the standard deviation of the dynamic nursing demand prediction index, obtain the demand pressure prediction index, mathematically described as... ,in, For the hospital area exist Demand pressure forecast index at any given time for Simulate scenarios at all times The dynamic nursing demand forecast index under the following conditions for Standard deviation of the dynamic nursing needs forecast index at any given time. [·] represents the expected value under various simulation scenarios. This is the risk aversion coefficient. The higher the value, the more conservative the system is, meaning it will reserve more manpower for uncertainty.

[0053] In this embodiment, the multidimensional competency-load matching model is constructed as follows:

[0054] S301: Extract nursing staff competency indicators based on the multi-hospital nursing data lake. The nursing staff competency indicators include skill level, training bonus, cumulative workload (i.e., the ratio of working time to the maximum allowed continuous working time), emotional fatigue index, and specialty matching degree.

[0055] S302: The real-time available competence is obtained based on the nursing staff competence index, mathematically described as follows: ,in, For the hospital area A nurse Real-time availability of competence at all times For the hospital area A nurse's basic competency score is the sum of standardized skill levels (e.g., linearly mapping levels 1-5 to the 0.6-1.0 range) and standardized training bonuses (e.g., 0.1 for ACLS certification, 0.05 for other certifications, with a maximum of 0.15). This is the load sensitivity coefficient (a constant greater than 0). For the hospital area The normalized cumulative workload of a nursing staff member For the hospital area The specialty matching degree of a nursing staff member (e.g., ICU specialist nurses have a score of 1 in the ICU ward and 0.7 in other wards). For the hospital area The emotional fatigue index of a nursing staff member (measured by wearable device data, with a value range of [0,1]). This is the fatigue effect coefficient (typical value is 0.3).

[0056] In this embodiment, step S4, the construction of the multi-objective overall utility function, includes: obtaining real-time human resource costs and the remaining budget within the period (the remaining amount after deducting the costs incurred in the period from the total human resource budget for this period); predicting and standardizing the expected nursing quality score using historical data; and obtaining the multi-objective overall utility function, mathematically described as follows: ,in, For multi-objective overall utility function, , and As weight, for Time Campus The total real-time available competence of all nursing staff in the country. Number of hospital campuses This refers to the total number of nursing staff in a single hospital ward. for Real-time human resource costs at any given moment for The remaining budget within the time period at any given moment. The standardized expected score for nursing quality; It represents the overall coordination effectiveness; the larger the value, the more reasonable and efficient the human resource coordination.

[0057] The fatigue accumulation constraint is specifically as follows: ,in, For nursing staff exist The cumulative fatigue over time, For nursing staff exist The cumulative fatigue over time, It is a forgetting factor, characterizing the natural recovery rate from fatigue. For nursing staff exist Cumulative workload at any given moment The fatigue bonus from additional tasks. This is an indicator function; it returns 1 if an additional task is scheduled this time, and 0 otherwise. This is a safety threshold;

[0058] The specific future risk constraints are as follows: ,in, The forward-looking strength coefficient (range [0,1]) represents a value of 0, where 0 indicates that the future is completely ignored and only current needs are met, while 1 indicates that current manpower is allocated entirely according to the maximum future pressure demand. The logic of the future risk constraint is that the total capacity allocated to a hospital area must not only meet current needs but also additionally meet a portion of the expected future growth demand. When coordinating manpower across multiple hospital areas, it is necessary to ensure that the above two constraint mechanisms are met while maximizing the value of the multi-objective coordination utility function.

[0059] Example 2:

[0060] A multi-hospital collaborative nursing demand forecasting and human resource coordination system includes a data processing module, a demand assessment module, a competency assessment module, and a human resource coordination module.

[0061] The data processing module is used to collect multi-source data from multiple hospital areas and integrate and clean it to obtain a multi-hospital nursing data lake.

[0062] The demand assessment module is used to construct a dynamic nursing demand assessment model based on the multi-hospital nursing data lake to obtain a dynamic nursing demand index and a demand pressure prediction index.

[0063] The competency assessment module is used to construct a multidimensional competency-load matching model for nursing staff based on the multi-hospital nursing data lake, and obtain real-time available competencies.

[0064] The human resource coordination module is used to construct a multi-hospital collaborative human resource coordination model based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence. The construction of the multi-hospital collaborative human resource coordination model includes the construction of a multi-objective coordination utility function and the introduction of a dynamic ethical constraint mechanism, which includes fatigue accumulation constraints and future risk constraints.

[0065] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A multi-institutional collaborative nursing demand prediction and human resource planning method, characterized by, The implementation of the nursing needs forecasting and human resource allocation method includes the following steps: S1: Collect multi-source data from multiple hospital areas, integrate and clean the data to obtain a multi-hospital nursing data lake; S2: Based on the multi-hospital nursing data lake, a dynamic nursing demand assessment model is constructed to obtain the dynamic nursing demand index and the demand pressure prediction index; S3: Construct a multi-dimensional competency-load matching model based on the multi-hospital nursing data lake to obtain real-time available competencies; S4: Based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence, a multi-hospital collaborative human resource coordination model is constructed. The construction of the multi-hospital collaborative human resource coordination model includes the construction of a multi-objective coordination utility function and the introduction of a dynamic ethical constraint mechanism. The construction of the multi-objective overall utility function includes: obtaining real-time labor costs and remaining budget within the period; predicting and standardizing the expected score of care quality using historical data; and obtaining the multi-objective overall utility function, mathematically described as follows: ,in, For multi-objective overall utility function, , and As weight, for Time Campus The total real-time available competence of all nursing staff in the country. Number of hospital campuses This refers to the total number of nursing staff in a single hospital ward. for Real-time human resource costs at any given moment for The remaining budget within the time period at any given moment. This represents the standardized expected score for nursing quality. For the hospital area exist Dynamic nursing needs index at any given moment; The dynamic ethical constraint mechanism includes fatigue accumulation constraint and future risk constraint; the fatigue accumulation constraint specifically is... ,in, For nursing staff exist The cumulative fatigue over time, For nursing staff exist The cumulative fatigue over time, Forgetting factor, For nursing staff exist Cumulative workload at any given moment The fatigue bonus from additional tasks. For indicator functions, The safety threshold is defined as follows: The specific future risk constraints are: ,in, Forward-looking strength coefficient, For the hospital area exist Demand pressure forecast index at any given time.

2. The method for predicting nursing needs and coordinating human resources across multiple hospital campuses according to claim 1, characterized in that, The construction of the dynamic nursing needs assessment model in step S2 is specifically as follows: S201: Extract real-time nursing demand features based on the multi-hospital nursing data lake. The real-time nursing demand features include the total number of patients, the proportion of high-risk patients, the total number of nursing operations, real-time infection risk indicators, and the proportion of patients transferred from the emergency department. S202: Based on the real-time nursing demand characteristics, the dynamic nursing demand index and the demand pressure prediction index are obtained; S203: The dynamic nursing demand assessment model is obtained based on the dynamic nursing demand index and the demand pressure prediction index.

3. The method for predicting nursing needs and coordinating human resources across multiple hospital campuses according to claim 2, characterized in that, Step S202 specifically includes: The mathematical description of the dynamic care demand index is... ,in, For the hospital area exist The dynamic nursing needs index at any given moment. For the hospital area exist The percentage of high-risk patients at any given time For a unit of time, the hospital area Total number of nursing procedures For the hospital area exist Total number of patients at any given time For the hospital area exist Real-time infection risk indicators at any given moment. For the hospital area exist The percentage of patients transferred to the emergency room at any given time. , , and As weight, [·] represents Z-Score standardization; The acquisition of the demand stress prediction index specifically involves: pre-setting a set of simulated scenarios; acquiring the dynamic nursing demand prediction index under the simulated scenarios; acquiring the standard deviation of the dynamic nursing demand prediction index; and obtaining the demand stress prediction index based on the dynamic nursing demand prediction index and the standard deviation of the dynamic nursing demand prediction index, mathematically described as follows: ,in, For the hospital area exist Demand pressure forecast index at any given time for Simulate scenarios at all times The dynamic nursing demand forecast index under the following conditions for Standard deviation of the dynamic nursing needs forecast index at any given time. [·] represents the expected value. This represents the risk aversion coefficient.

4. The method for predicting nursing needs and coordinating human resources across multiple hospital campuses according to claim 1, characterized in that, The construction of the multidimensional competency-load matching model in step S3 is as follows: Nursing staff competency indicators were extracted based on the multi-hospital nursing data lake. These indicators include skill level, training bonus, cumulative workload, emotional fatigue index, and specialty matching degree. The real-time available competence is obtained based on the aforementioned nursing staff competence index, and is mathematically described as follows: ,in, For the hospital area A nurse Real-time availability of competence at all times For the hospital area A nurse's basic competency score is the sum of their standardized skill level and standardized training bonus points. For load sensitivity coefficient, For the hospital area The normalized cumulative workload of a nursing staff member For the hospital area Specialty matching degree of a certain nursing staff For the hospital area The emotional fatigue index of a nursing staff member This represents the fatigue effect coefficient.

5. A multi-hospital collaborative nursing demand prediction and human resource coordination system, characterized in that, The system is applied to the multi-hospital collaborative nursing demand prediction and human resource coordination method as described in any one of claims 1-4, including a data processing module, a demand assessment module, a competency assessment module, and a human resource coordination module. The data processing module is used to collect multi-source data from multiple hospital areas and integrate and clean it to obtain a multi-hospital nursing data lake. The demand assessment module is used to construct a dynamic nursing demand assessment model based on the multi-hospital nursing data lake to obtain a dynamic nursing demand index and a demand pressure prediction index. The competency assessment module is used to construct a multidimensional competency-load matching model based on the multi-hospital nursing data lake to obtain real-time available competencies. The human resource coordination module is used to construct a multi-hospital collaborative human resource coordination model based on the dynamic nursing demand index, the demand pressure prediction index, and the real-time available competence. The construction of the multi-hospital collaborative human resource coordination model includes the construction of a multi-objective coordination utility function and the introduction of a dynamic ethical constraint mechanism, which includes fatigue accumulation constraints and future risk constraints.

Images