An obstetric medical resource scheduling method and system

Abstract

The application provides an obstetric medical resource scheduling method and system, which comprises the following steps: determining the estimated time consumption of each task step in a resource combination process according to refined state information, personnel real-time location information and task information, and calculating the estimated completion time of the resource combination process according to the estimated time consumption of the task step; generating a preliminary resource scheduling scheme; simulating the preliminary resource scheduling scheme based on the refined state information, the personnel real-time location information, the task information and the estimated completion time of the resource combination process to identify the resource state conflict, the time conflict or the personnel response capability conflict existing in the preliminary resource scheduling scheme; adjusting the preliminary resource scheduling scheme or generating an alternative scheme according to the identified conflict, and generating a final resource scheduling instruction in the case that the simulation result shows no conflict or the conflict has been solved. The application effectively solves the problems of inaccurate scheduling and low efficiency of the existing system in an emergency.

Description

Technical Field

[0001] This application relates to the field of obstetric medical resource allocation, and more specifically, to a method and system for obstetric medical resource allocation. Background Technology

[0002] In modern healthcare institutions, especially in obstetrics, the efficient allocation of medical resources is crucial for maternal and infant safety. Existing resource allocation systems typically rely on static availability and pre-defined rules. However, these systems face significant challenges when dealing with urgent, high-risk situations requiring rapid, dynamic resource reallocation. Specifically, they often overlook the actual time and effort involved in preparing resources (such as mobile equipment, sterilization, or getting professionals on-site), leading to delays and inefficiencies at critical moments. Summary of the Invention

[0003] This application discloses a method and system for scheduling obstetric medical resources, which aims to solve the problems of existing obstetric medical resource scheduling systems neglecting the actual time and effort consumed in the resource preparation process when dealing with emergency and high-risk situations, resulting in scheduling delays and low efficiency, as well as the inability to effectively identify and resolve resource status conflicts, time conflicts, or personnel response capability conflicts.

[0004] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application discloses a method for allocating obstetric medical resources, comprising the following steps: Acquire detailed status information of obstetric medical equipment, including information on the preparation process for the equipment to transition from a non-ready state to a ready state; Obtain real-time location and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. A pre-defined resource combination process for obstetric emergency scenarios, which includes multiple task steps; Based on refined status information, real-time location information of personnel, and task information, the estimated time for each task step in the resource combination process is determined, and the estimated completion time of the resource combination process is calculated based on the estimated time for each task step. Generate a preliminary resource scheduling plan; Based on refined status information, real-time location information of personnel, task information, and the estimated completion time of resource combination process, a preliminary resource scheduling plan is simulated to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling plan. Based on the identified conflicts, the initial resource scheduling plan is adjusted or an alternative plan is generated, and the final resource scheduling instruction is generated if the simulation results show no conflict or the conflict has been resolved. The final resource scheduling instructions will be issued to the relevant personnel.

[0005] Secondly, this application also discloses an obstetric medical resource scheduling system, which includes: The status information acquisition module is used to acquire detailed status information of obstetric medical equipment. The detailed status information includes the preparation process information of the equipment from non-ready state to ready state. The personnel information acquisition module is used to acquire the real-time location information and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. The process preset module is used to preset the resource combination process for obstetric emergency scenarios. The resource combination process includes multiple task steps. The time calculation module is used to determine the estimated time for each task step in the resource combination process based on refined status information, real-time location information of personnel, and task information, and to calculate the estimated completion time of the resource combination process based on the estimated time for each task step. The scheme generation module is used to generate preliminary resource scheduling schemes; The simulation and verification module is used to simulate the preliminary resource scheduling scheme based on refined status information, real-time location information of personnel, task information, and the estimated completion time of the resource combination process, so as to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling scheme. The scheme adjustment module is used to adjust the initial resource scheduling scheme or generate alternative schemes based on the identified conflicts, and generate the final resource scheduling instructions when the simulation results show no conflict or the conflict has been resolved. The instruction issuance module is used to issue the final resource scheduling instructions to the relevant personnel.

[0006] Compared with the prior art, this application has at least the following beneficial effects: This application, by acquiring detailed status information of obstetric medical equipment and real-time location and task information of key obstetric personnel, can comprehensively and in real-time grasp the most accurate status and availability of medical resources. Based on this, a resource combination process for obstetric emergency scenarios is pre-defined, and the estimated time for each task step is determined according to the detailed information. This allows for the calculation of the estimated completion time of the entire resource combination process, overcoming the shortcomings of existing systems that rely solely on static availability while ignoring the actual time consumption of resource preparation.

[0007] This application simulates a preliminary resource scheduling scheme and, based on refined status information, real-time location information, task information, and the estimated completion time of the resource combination process, can identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary scheme. This simulation verification mechanism effectively solves the problem that existing systems cannot foresee and avoid potential conflicts, and avoids scheduling delays caused by equipment not being disinfected in time, personnel not being able to arrive in time, or insufficient equipment installation and debugging time.

[0008] Based on the identified conflicts, this application's system can intelligently adjust the initial plan or generate alternative plans. When simulation results show no conflict or that the conflict has been resolved, the system generates final resource scheduling instructions and issues them to relevant personnel. This makes the scheduling instructions more feasible and accurate, avoiding the uncertainties caused by human intervention and experience-based judgment, and significantly improving the efficiency and safety of medical resource scheduling in obstetric emergency scenarios. Compared to existing technologies, this application fundamentally solves the scheduling errors and delays caused by incomplete information and inaccurate predictions, ensuring that necessary resources can be quickly and accurately allocated at critical moments, thereby effectively protecting maternal and infant safety. Attached Figure Description

[0009] Figure 1 A flowchart illustrating a method for allocating obstetric medical resources provided in this application; Figure 2 This is a schematic diagram of the structure of an obstetric medical resource scheduling system provided in this application. Detailed Implementation

[0010] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0011] like Figure 1 As shown in the embodiment of this application, a method for scheduling obstetric medical resources is proposed, including: Acquire detailed status information of obstetric medical equipment, including information on the preparation process for the equipment to transition from a non-ready state to a ready state; Obtain real-time location and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. A pre-defined resource combination process for obstetric emergency scenarios, which includes multiple task steps; Based on refined status information, real-time location information of personnel, and task information, the estimated time for each task step in the resource combination process is determined, and the estimated completion time of the resource combination process is calculated based on the estimated time for each task step. Generate a preliminary resource scheduling plan; Based on refined status information, real-time location information of personnel, task information, and the estimated completion time of resource combination process, a preliminary resource scheduling plan is simulated to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling plan. Based on the identified conflicts, the initial resource scheduling plan is adjusted or an alternative plan is generated, and the final resource scheduling instruction is generated if the simulation results show no conflict or the conflict has been resolved. The final resource scheduling instructions will be issued to the relevant personnel.

[0012] This application, by introducing refined status information, real-time location information of personnel, and task information, and combining it with a simulation verification mechanism, can more accurately assess resource availability and the effectiveness of scheduling schemes, thereby significantly improving the efficiency and safety of resource scheduling in obstetric emergency scenarios.

[0013] To better understand the obstetric medical resource allocation method proposed in this application, some key terms involved are explained.

[0014] Detailed status information for obstetric medical equipment refers to information that goes beyond simple availability or occupancy, delving into the specific preparation processes required to transition the equipment from a non-ready state (e.g., recently used, being sterilized, requiring maintenance) to a ready state (ready for immediate use). This includes the equipment's cleanliness, sterilization cycle, calibration requirements, consumable reserves, and the time required for any physical movement or installation.

[0015] Real-time location information of key personnel in obstetrics refers to the current geographical location of key personnel such as medical staff and technicians, which is obtained in real time through positioning technologies (such as GPS, Wi-Fi positioning, Bluetooth beacons, etc.).

[0016] Task information refers to the details of the tasks that key personnel are currently performing, including task type, estimated start time, estimated completion time, and task priority.

[0017] The resource combination process for obstetric emergency scenarios refers to a set of standard operating procedures and required resources pre-set for specific obstetric emergency situations (such as placental abruption, postpartum hemorrhage, neonatal asphyxia, etc.). Each process consists of multiple task steps, such as preparing the operating room, allocating the neonatal resuscitation table, and summoning anesthesiologists.

[0018] Resource status conflict refers to a situation in the initial resource scheduling plan where a device or resource, when being scheduled, shows in its refined status information that it cannot reach the ready state at the required time.

[0019] A time conflict refers to a situation in the initial resource scheduling plan where the estimated time for a certain task step overlaps with the existing schedule or cannot meet urgent time requirements.

[0020] Personnel responsiveness conflict refers to a situation in the initial resource scheduling plan where the immediate location, current task, or skill level of a key personnel cannot meet the task requirements for being scheduled.

[0021] The method for allocating obstetric medical resources in this application is described in detail below: First, detailed status information of obstetric medical equipment is obtained. For example, sensors can be installed on each piece of equipment to monitor its operational status, cleaning status, sterilization progress, and consumable reserves in real time. Furthermore, integration with a Hospital Information System (HIS) or Equipment Management System (EMS) can automatically acquire equipment maintenance records, calibration plans, and other information. This information collectively constitutes the detailed status information of the equipment. For instance, after a neonatal resuscitation table has been used once, its status will change from "in use" to "awaiting sterilization," then proceed through several preparation processes such as sterilization and testing, until it finally becomes "ready." Another approach is to manually input or scan QR codes on the equipment, allowing medical staff or equipment administrators to manually update the equipment's current status and preparation process information.

[0022] Secondly, it is necessary to obtain the real-time location and task information of key personnel in the obstetrics department. For example, a positioning module can be integrated into the name tags or mobile devices worn by medical staff to track their location within the hospital in real time. Simultaneously, by interfacing with the hospital's scheduling system, electronic medical record system, or task management system, the system can obtain the tasks currently being performed, their priorities, and estimated completion times. For instance, an anesthesiologist's real-time location information might show them in operating room A, and their task information might indicate they are performing an elective surgery, expected to be completed in 30 minutes. Another approach is to deploy Bluetooth beacons or Wi-Fi hotspots throughout the hospital, combined with a mobile application, allowing medical staff to manually check in or for the system to automatically identify their location. Medical staff can then manually update their task status and estimated completion time via the application.

[0023] Furthermore, pre-defined resource combination processes for obstetric emergency scenarios can be implemented. For example, for an emergency scenario of acute placental abruption, a pre-defined resource combination process can be developed, encompassing multiple task steps such as preparation for emergency cesarean section, neonatal resuscitation preparation, and prevention of postpartum hemorrhage. Each task step clearly defines the required equipment, personnel, and facilities. These processes can be defined and configured by clinical experts according to standard operating procedures (SOPs) and stored in the scheduling system's database.

[0024] Then, based on refined status information, real-time personnel location information, and task information, the estimated time for each task step in the resource integration process is determined, and the estimated completion time of the resource integration process is calculated based on the estimated time of each task step. For example, in the task step of preparing for an emergency cesarean section, if a mobile neonatal resuscitation table needs to be deployed, the system will calculate the estimated time for the device to reach a ready state based on the table's refined status information (e.g., currently awaiting sterilization), combined with the time required for sterilization, movement, and installation / calibration. Simultaneously, the system will assess the estimated time for the anesthesiologist to arrive at the operating room and be ready based on their real-time location and task information. By summing the estimated times of all task steps, the estimated completion time of the entire resource integration process can be obtained.

[0025] Next, a preliminary resource scheduling plan is generated. For example, based on the current available resources and personnel, and combined with preset resource combination processes, the system will automatically generate a preliminary scheduling plan, including designating operating rooms, allocating equipment, and assigning medical staff.

[0026] Subsequently, based on refined status information, real-time personnel location information, task information, and the estimated completion time of the resource combination process, a preliminary resource scheduling plan is simulated to identify resource status conflicts, time conflicts, or personnel responsiveness conflicts within the preliminary plan. For example, the system simulates whether all equipment and personnel can be ready at the required time under the preliminary plan. If the simulation finds that the scheduled resuscitation table is still being sterilized at the required time, a resource status conflict is identified. If the anesthesiologist is still performing other tasks at the scheduled surgery start time, a time conflict or personnel responsiveness conflict is identified.

[0027] Finally, based on the identified conflicts, the initial resource scheduling plan is adjusted, or alternative plans are generated. If the simulation results show no conflicts or that the conflicts have been resolved, the final resource scheduling instructions are generated. For example, if a resource status conflict for the resuscitation table is identified, the system may attempt to find another available resuscitation table or adjust the surgery start time. If a conflict in personnel responsiveness is identified, the system may attempt to assign another medical staff member with the appropriate skills. Once all conflicts are resolved, the system generates a detailed final scheduling instruction, including equipment allocation paths, personnel task assignments, and timeframes.

[0028] Finally, the final resource allocation instructions are issued to the relevant personnel. For example, the instructions are sent to relevant medical staff, equipment department staff, and logistics staff through the hospital's communication system (such as SMS, mobile app push notifications, voice broadcasts, etc.) to ensure that they can receive and execute the instructions in a timely manner.

[0029] This application, by introducing refined status information, real-time personnel location information, and task information, enables a more comprehensive and accurate assessment of the true availability of obstetric medical resources. Traditional systems only focus on whether resources are idle, while this application delves into the preparation process from unready to ready, thus avoiding delays caused by insufficient preparation time. For example, in a traditional system, a device that has just been used but has not yet been sterilized might be marked as idle; however, in this application, the device is marked as awaiting sterilization, and the time required for its sterilization, testing, and other preparation processes is calculated, thereby preventing it from being mistakenly assigned to emergency tasks.

[0030] Furthermore, this application, through simulation verification of the preliminary scheduling scheme, can identify potential resource status conflicts, time conflicts, and personnel response capability conflicts in advance. This is fundamentally different from the traditional system's approach of discovering problems only after scheduling instructions are issued. Through simulation, the system can identify and resolve problems before actual execution, thereby avoiding valuable time losses caused by scheduling errors in emergency situations. For example, in traditional systems, dispatchers may manually allocate resources in emergency situations, but due to a lack of information transparency, equipment or personnel may not be able to arrive in time. This application, through simulation, can anticipate these problems and provide adjustment or alternative solutions, thereby ensuring the effectiveness and feasibility of scheduling instructions.

[0031] When simulating preliminary resource scheduling schemes to identify resource status conflicts, time conflicts, or personnel response capability conflicts, the complex preparation process of high-precision medical equipment in specific microenvironments may not be fully considered. For example, the activation of advanced functions of some high-precision medical equipment not only depends on its own basic preparation time, but may also be significantly affected by environmental parameters (such as temperature, humidity, and vibration). If these environmental factors are not accurately assessed, the equipment may not be ready in time at the scheduled point, thus triggering potential scheduling conflicts and affecting emergency response efficiency and patient safety.

[0032] In response, this application further proposes the following steps for simulating the preliminary resource scheduling scheme based on refined status information, real-time personnel location information, task information, and the estimated completion time of the resource combination process, in order to identify resource status conflicts, time conflicts, or personnel response capability conflicts existing in the preliminary resource scheduling scheme: Acquire parameter information of the microenvironment in which the high-precision medical device is located, including temperature, humidity or vibration; Based on parameter information and the pre-set environmental sensitivity curve inside the high-precision medical device, calculate the additional preparation time required for the advanced functions of the high-precision medical device. The additional preparation time is added to the basic preparation time of the high-precision medical equipment to obtain the expected functional readiness time of the high-precision medical equipment. Based on the expected functional readiness time, determine whether the advanced functions of high-precision medical equipment can be activated in time as required by the initial resource scheduling plan. If higher-level functions cannot be activated in time as required by the initial resource scheduling scheme, a higher-level function readiness conflict is identified.

[0033] Specifically, acquiring parameter information of the microenvironment in which high-precision medical devices exist refers to collecting physical parameters of the surrounding environment, such as temperature, humidity, or vibration, in real time through sensors or other monitoring devices. These parameters have a critical impact on the performance and startup time of certain precision equipment. High-precision medical devices can be understood as medical devices that are sensitive to environmental conditions, have complex startup or calibration processes, and whose advanced functions are crucial to emergency treatment outcomes, such as advanced ultrasound diagnostic instruments, neonatal incubators, and extracorporeal membrane oxygenation (ECMO) devices.

[0034] Furthermore, the environmental sensitivity curve is preset through historical data analysis and describes the functional relationship between the time required for the device to start up or stabilize its higher-order functions under different environmental parameters. For example, in low-temperature or high-humidity environments, some devices may require longer preheating or dehumidification times to reach optimal operating conditions. By consulting or calculating this curve, the impact of environmental factors on device preparation time can be quantified, thus obtaining an additional preparation time.

[0035] Therefore, by adding the additional preparation time to the basic preparation time of the high-precision medical equipment, we obtain the estimated functional readiness time of the high-precision medical equipment. The basic preparation time refers to the shortest time required for the equipment to transition from a non-ready state to a higher-order functional ready state under ideal environmental conditions. By adding the additional preparation time, we can obtain an estimated functional readiness time that is closer to reality and takes into account environmental impacts.

[0036] Subsequently, based on the projected functional readiness time, it is determined whether the advanced functions of the high-precision medical device can be activated in a timely manner as required by the initial resource scheduling plan. This determination process involves comparing the calculated projected functional readiness time with the activation time set for the advanced functions of the device in the initial resource scheduling plan. If the projected functional readiness time is later than the required activation time, it indicates a potential problem.

[0037] Finally, if higher-order functions cannot be activated in time as required by the initial resource scheduling plan, a higher-order function readiness conflict is identified. The identification of this conflict indicates an inadequacy in the initial scheduling plan's allocation of the high-precision device, requiring further adjustments or the generation of an alternative plan.

[0038] This application addresses the issue of simulation schemes potentially neglecting environmental factors, leading to equipment failure to reach readiness on time, by introducing the perception and analysis of microenvironmental parameters of high-precision medical equipment. Specifically, by acquiring parameters such as temperature, humidity, or vibration of the equipment's microenvironment and combining them with the equipment's preset environmental sensitivity curve, the additional preparation time required for the activation of higher-order functions due to environmental factors can be accurately calculated. By adding this additional preparation time to the equipment's base preparation time, the system obtains a more accurate predicted functional readiness time. Furthermore, by comparing this predicted functional readiness time with the time points required in the initial scheduling scheme, conflicts in the high-order functional readiness of high-precision medical equipment can be promptly detected and identified, thereby avoiding equipment delays caused by environmental influences and ensuring the reliability and feasibility of the scheduling scheme.

[0039] In some of the above embodiments, the steps of adjusting the preliminary resource scheduling scheme or generating an alternative scheme based on the identified conflicts, and generating the final resource scheduling instruction when the simulation results show no conflicts or the conflicts have been resolved, further include: Generate a summary view containing multiple alternatives. The summary view highlights the estimated readiness time for each alternative, the actual arrival time of the required critical equipment and personnel, and potential minor risk warnings. Based on the pre-set obstetric emergency priority rules, a preliminary risk assessment is conducted for each alternative, and the risk assessment results are displayed in the summary view using color coding or risk level marking. Provides an interactive timeline view that shows the parallel and serial relationships of tasks in each alternative, as well as key milestone dates; In response to receiving a dispatcher's instruction to select one of multiple alternatives, a partial simulation of that alternative is performed in the virtual emergency rescue sandbox; Record the dispatcher's historical selection preferences and decision-making patterns; Based on historical selection preferences and decision-making patterns, alternatives that align with the scheduler's preferences or have been successfully adopted in similar situations are given priority.

[0040] Specifically, a summary view containing multiple alternatives is generated to provide dispatchers with a quick and intuitive overview, enabling them to rapidly understand the core information of each alternative in an emergency. The summary view is designed to highlight key decision-making factors, such as the estimated readiness time for each alternative, which helps dispatchers assess the timeliness of the plan; the actual arrival time of required critical equipment and personnel, which directly relates to the availability of emergency resources; and potential secondary risks, allowing dispatchers to anticipate potential problems.

[0041] The process involves conducting a preliminary risk assessment for each alternative plan based on pre-defined obstetric emergency priority rules. The aim is to quantify and visualize the potential risks of each plan. These priority rules can be pre-defined based on clinical guidelines, expert experience, or historical data; for example, fetal distress and postpartum hemorrhage can be assigned high priority. Risk assessment results can be displayed in a summary view using color coding (e.g., red for high risk, yellow for medium risk, and green for low risk) or risk level indicators (e.g., Level 1 risk, Level 2 risk), allowing dispatchers to easily identify the level of risk and assisting them in making decisions regarding risk avoidance or risk acceptance.

[0042] In practical applications, an interactive timeline view is provided to help schedulers gain a deeper understanding of the execution flow and time dependencies of each alternative. The timeline view clearly shows the parallel and sequential relationships between tasks within each alternative; for example, equipment preparation and personnel readiness can be performed in parallel, while the start of surgery must be performed sequentially after both equipment and personnel are ready. Simultaneously, the timeline view also displays key milestone dates, such as the estimated surgery start time and estimated delivery time, which is crucial for schedulers to conduct refined management and expectation management.

[0043] Furthermore, in response to receiving a dispatcher's instruction to select one of several alternatives, a partial simulation of that alternative is performed in the virtual emergency response sandbox. The purpose is to validate the selected alternative before actual execution. The virtual emergency response sandbox is a simulation environment that allows dispatchers to practice specific plans without affecting real emergency response procedures, to confirm their feasibility, identify potential secondary conflicts, or optimize execution details. Partial simulations can focus on key aspects of the selected plan; for example, simulating the availability of specific equipment at a specific point in time, or the response path for specific personnel.

[0044] Furthermore, recording dispatchers' historical selection preferences and decision-making patterns aims to construct personalized decision-making models for dispatchers. Historical selection preferences can include the types of options dispatchers tend to choose in different emergency response scenarios (e.g., prioritizing speed, prioritizing resource adequacy, or prioritizing specific personnel), while decision-making patterns can reflect dispatchers' behavioral characteristics when facing risks, time pressure, or information uncertainty.

[0045] Therefore, based on historical selection preferences and decision-making patterns, the system prioritizes recommending alternatives that align with dispatcher preferences or have been successfully adopted in similar situations. The aim is to provide dispatchers with intelligent decision support. By learning from dispatchers' past experiences and success stories, the system can predict the options dispatchers might choose and place them in a more prominent position, thereby accelerating the decision-making process and improving the accuracy and efficiency of decisions, especially under high-pressure environments.

[0046] This application effectively addresses the decision-making dilemma that dispatchers may face when confronted with multiple alternatives in the basic solution by introducing multi-dimensional information display, intelligent risk assessment, interactive process visualization, and personalized decision recommendation mechanisms. Specifically, the combination of summary view, risk assessment, and timeline view enables dispatchers to comprehensively and quickly grasp the core information of each alternative from macro to micro perspectives, and from risk to process, greatly reducing the complexity of information processing and cognitive load. The local simulation in the virtual emergency rescue sandbox provides dispatchers with an opportunity for trial and error, allowing them to verify the effectiveness of their chosen solutions in a risk-free environment, thereby enhancing their confidence and accuracy in decision-making. Simultaneously, by recording and learning dispatchers' historical selection preferences and decision-making patterns, the system can provide customized, experience-driven recommendations. This not only accelerates the decision-making process but, more importantly, integrates the dispatcher's personal experience and wisdom into the automated dispatch process, enabling the system to provide more intelligent and human-centered decision support in emergency situations. It is precisely due to the synergistic effect of these additional technical features that dispatchers can select the optimal resource dispatch solution more efficiently and accurately.

[0047] Through the aforementioned technical solution, this application can significantly reduce the cognitive load of dispatchers in obstetric emergency scenarios, especially when facing complex and ever-changing resource conflicts and multiple alternatives. This solution provides structured and visual information displays (such as summary views and timeline views), enabling dispatchers to quickly understand the advantages, disadvantages, and potential risks of each option, thereby improving decision-making efficiency and accuracy. Furthermore, the introduced risk assessment mechanism and virtual emergency sandbox partial simulation function provide dispatchers with tools for decision verification and risk prediction, effectively avoiding suboptimal decisions due to insufficient information or misjudgment. More importantly, by learning and utilizing dispatchers' historical selection preferences and decision-making patterns, the system can provide personalized intelligent recommendations. This not only accelerates the decision-making process but also makes the final dispatch instructions more consistent with actual operating habits and successful experiences, thereby comprehensively improving the intelligence level of obstetric medical resource dispatch and the success rate of emergency response.

[0048] In some of the above embodiments, the step of generating a summary view containing multiple alternatives, highlighting the estimated readiness time of each alternative, the actual arrival time of the required critical equipment and personnel, and potential secondary risks includes: The system senses the scheduler's interaction with the summary view, including the scheduler's focus area, interaction duration, or click or hover actions on specific information elements. Dynamically adjust the presentation or level of detail of information in the summary view based on interactive behavior; When the focus area is on the estimated readiness time for an extended period of time, the parallel and serial relationships of key tasks in the alternative solution or the estimated time of each task are overlaid. When the interaction involves clicking or hovering over a minor risk warning, a risk details window pops up, showing the clinical impact, probability of occurrence, or urgency of the risk. The density of information in the summary view is dynamically adjusted based on the dispatcher's perceived load status. When cognitive load is high, the information density in the simplified summary view is reduced to show only the estimated readiness time, the actual arrival time of the required critical equipment and personnel, and secondary risks are highlighted with icons. When cognitive load is moderate, expand the density of information in the summary view to display more detailed information.

[0049] Specifically, the system can perceive and capture the dispatcher's interactions with the summary view in real time. These interactions can include the dispatcher's gaze focus area, such as using eye-tracking technology to capture specific areas the dispatcher focuses on on the screen; the duration of interaction with the interface, such as the time spent on a particular information element; or clicks or hovering actions on specific information elements, such as clicking a button or hovering the mouse over a tooltip. This interaction data is used to assess the dispatcher's focus and level of interest in the current information.

[0050] Based on the perceived interaction behavior, the presentation method or level of detail of information in the summary view can be dynamically adjusted. For example, when the system detects that the scheduler's gaze is focused on the estimated readiness time of an alternative for an extended period, in order to provide deeper information support, the system can automatically overlay the parallel and serial relationships of key tasks in that alternative, or display the estimated time of each task, thereby helping the scheduler understand the specific composition and potential time risks behind the estimated readiness time.

[0051] When a dispatcher's interaction involves clicking or hovering over a minor risk warning, the system can immediately display a risk details window. This window aims to provide more detailed information about the minor risk, such as its clinical impact (the potential effect on patients or medical procedures), its probability of occurrence (the likelihood of the risk occurring in the current context), or its urgency (the level of urgency required to address the risk). In this way, dispatchers can quickly obtain comprehensive information about the risk to make more informed decisions.

[0052] This application also dynamically adjusts the information density in the summary view based on the dispatcher's cognitive load. Cognitive load can be assessed in various ways, such as through physiological signal monitoring or human-computer interaction behavior analysis. When the dispatcher's cognitive load is judged to be high, to avoid information overload, the system automatically reduces the information density in the summary view, displaying only the most core and critical information, such as the estimated readiness time, the actual arrival time of required key equipment and personnel, and highlighting potential secondary risks with icons to ensure the dispatcher can quickly grasp the key points. Conversely, when the dispatcher's cognitive load is moderate, the system can expand the information density in the summary view, displaying more detailed information to meet the dispatcher's need for comprehensive information.

[0053] This application effectively solves the problems of information overload and omission of key information that dispatchers may face under a fixed information display mode by sensing the dispatcher's interactive behavior and cognitive load in real time and dynamically adjusting the information presentation of the summary view accordingly. Specifically, when the dispatcher's gaze is focused on the estimated readiness time for a long time, the system proactively provides more in-depth task time breakdown information, enabling the dispatcher to quickly understand the details of the time composition, thereby avoiding decision hesitation caused by insufficient information. When the dispatcher shows interest in secondary risk prompts, the system immediately pops up detailed risk information, allowing the dispatcher to obtain the clinical impact, probability of occurrence, and urgency of the risk without additional operation. This helps the dispatcher to comprehensively assess the risk and avoids risk misjudgment due to untimely or incomplete information. More importantly, by dynamically adjusting the information density according to the dispatcher's cognitive load, this application ensures that only the most core and urgent information is presented when the dispatcher is under high load, effectively reducing cognitive burden and avoiding decision fatigue; while when the load is moderate, more comprehensive information is provided to meet the dispatcher's need for detailed understanding. This adaptive information presentation mechanism enables dispatchers to acquire and process information in an optimal way under different pressures and cognitive states, thereby significantly improving the efficiency and accuracy of decision-making.

[0054] Through the above technical solution, this application can significantly improve the efficiency and accuracy of resource scheduling decisions in obstetric emergency scenarios. The summary view in the basic solution may lead to difficulties for dispatchers in quickly filtering key information in emergency situations due to fixed information, or cognitive load due to excessive information volume. This embodiment achieves intelligent adaptive adjustment of the summary view by dynamically sensing the dispatcher's interactive behavior and cognitive load status. This allows dispatchers to receive information that matches their current focus and cognitive ability under high-pressure environments, avoiding information overload or omission of key information, thereby shortening decision-making time and reducing the risk of misjudgment. Especially when cognitive load is high, the concise information density and highlighted prompts help dispatchers quickly focus on core issues, ensuring that the most critical decisions can be made in the most urgent moments. This human-centered information presentation method greatly optimizes the human-computer interaction experience, improves the practicality and reliability of the scheduling system, and ultimately helps improve the clinical outcomes of obstetric emergency care.

[0055] In some of the embodiments described above in this application, a method is proposed to record dispatchers' historical selection preferences and decision-making patterns, and to prioritize and recommend alternatives based on these preferences and patterns. However, in its implementation, dispatchers' decision-making behavior may be influenced by various factors, especially in high-pressure emergency situations, where their cognitive load may fluctuate significantly, leading to deviations in decision-making patterns. If these deviations in decision-making and the underlying cognitive load are not accurately captured and analyzed, it may affect the guiding role of historical data for future recommendations, and may even cause the system's recommended solutions to be inconsistent with the dispatcher's actual needs or best practices.

[0056] In this regard, this application further proposes that the steps for recording the dispatcher's historical selection preferences and decision-making patterns include: Perceive the cognitive load status of the dispatcher; When the cognitive load reaches a preset threshold, the scheduler's decision-making behavior is flagged; By comparing the decision-making behavior of the marked individuals with the dispatcher's typical decision-making patterns, deviations from the established decision-making process can be identified. Analyze the effects of deviations from the decision-making process on clinical outcomes; Adjust the weight of deviations from the decision in historical choice preferences and decision-making patterns based on the implementation effect and clinical results.

[0057] Specifically, perceiving the cognitive load status of dispatchers refers to acquiring information on their psychological and physiological states during decision-making in real time or near real time through various technical means to assess their current workload level. For example, physiological signals of dispatchers (such as heart rate, skin conductance, eye movement data, etc.) or their operational behaviors on human-computer interaction interfaces (such as mouse click frequency, keyboard input speed, and gaze focus area, etc.) can be collected to comprehensively determine their cognitive load level.

[0058] Specifically, when cognitive load reaches a preset threshold, the dispatcher's decision-making behavior is marked. This means that when the system detects that the dispatcher's cognitive load level exceeds a pre-set threshold, the dispatching decisions made by the dispatcher at that moment are specially marked. This preset threshold can be set based on clinical experience, expert knowledge, or historical data analysis, aiming to identify decisions that may be made under high-pressure or high-load conditions.

[0059] Identifying deviations in decision-making by comparing labeled decision-making behaviors with the dispatcher's conventional decision-making patterns involves comparing these labeled decisions with the decisions that dispatchers typically make under normal cognitive load or in similar situations. Conventional decision-making patterns can be formed through long-term observation and data accumulation, reflecting the dispatcher's preferences and habits under steady-state conditions. By comparing these patterns, decisions that deviate from the conventional patterns and may be influenced by high cognitive load can be identified.

[0060] Analyzing the implementation effects and clinical outcomes of deviated decisions refers to tracking and evaluating the implementation of these identified deviated decisions in actual emergency scenarios. This includes collecting logs of key events after decision implementation (such as equipment arrival time, personnel response time, and key operation completion time) as well as patient clinical outcome data (such as maternal and infant prognosis scores, complication rates, and length of hospital stay).

[0061] Adjusting the weight of deviated decisions in historical choice preferences and decision-making patterns based on implementation effectiveness and clinical outcomes means dynamically adjusting the importance of deviated decisions in historical data according to their actual effects. If a deviated decision achieves good implementation effectiveness and clinical outcomes under high cognitive load, its weight can be appropriately increased, indicating that the decision has reference value under specific high-pressure situations; conversely, if the effect is poor, the weight can be reduced to avoid over-adopting such decisions in future system recommendations.

[0062] This application, by introducing the perception and analysis of dispatchers' cognitive load status, enables a deeper understanding of the decision-making context of dispatchers in different situations. In the basic scheme, the recording of historical choice preferences and decision-making patterns may only focus on the decision outcome itself, ignoring the psychological state during the decision-making process. It is precisely because dispatchers' cognitive load may significantly increase in high-pressure emergency scenarios that their decision-making behavior deviates from the conventional pattern. This embodiment, by perceiving cognitive load status and labeling decisions made under high load, can distinguish between conventional and deviated decisions. Furthermore, by analyzing the actual implementation effects and clinical outcomes of these deviated decisions, the system can evaluate the effectiveness of these deviated decisions. This mechanism allows the system to dynamically adjust the weight of decisions in historical data based on their actual effects, thereby ensuring that the recorded historical choice preferences and decision-making patterns not only include experience under normal circumstances but also specific decisions that have been verified as effective or ineffective under high-pressure situations, making the historical data more instructive and robust.

[0063] Through the above technical solution, this application overcomes the limitation of failing to fully consider the dispatcher's cognitive load and its impact on decision-making when recording the dispatcher's historical selection preferences and decision-making patterns. This embodiment, through the perception of cognitive load, the identification of deviations from decisions, and the analysis of their effects, makes the recorded dispatcher's historical selection preferences and decision-making patterns more refined and intelligent. This not only more accurately reflects the dispatcher's true decision-making tendencies in different situations but also identifies and learns effective or ineffective decision-making strategies that may emerge under high-pressure situations. Therefore, when recommending alternative solutions, the system can provide recommendations that better match the dispatcher's current cognitive load and actual needs based on more comprehensive and context-adaptive historical data, thereby significantly improving the accuracy, reliability, and practicality of dispatching plans, ultimately optimizing the resource allocation efficiency and clinical outcomes of obstetric emergency care.

[0064] In some of the above embodiments, the steps for sensing the cognitive load status of the scheduler include: Collect the dispatcher's physiological signals; Data collection and dispatching personnel's operational behavior on the human-computer interaction interface; Sliding time window analysis is performed on physiological signals to capture instantaneous changes in physiological signals; Calculate the frequency and rate of change of operational behavior within a short time window to capture short-term changes in operational behavior; Correlating instantaneous changes in physiological signals with short-term changes in operational behavior; When both transient changes in physiological signals and short-term changes in operational behavior indicate high workload fluctuations, update the cognitive workload status. Output the level of cognitive load based on the updated cognitive load status.

[0065] Specifically, collecting physiological signals from dispatchers can include, but is not limited to, heart rate, heart rate variability, skin conductance, eye movement data, or electroencephalogram (EEG). These physiological signals can objectively reflect the dispatcher's physiological stress level and attention allocation during task execution. For example, an increased heart rate or a decreased heart rate variability may indicate a higher cognitive load.

[0066] Simultaneously, the system collects data on dispatchers' operational behaviors on the human-computer interface, such as mouse click frequency, keyboard input speed, cursor movement trajectory, interface switching frequency, and activation status of specific function buttons. This operational behavior data directly reflects the efficiency and smoothness of the dispatcher's interaction with the system, as well as whether there is hesitation or error in operation, thereby indirectly reflecting their cognitive load level.

[0067] To more accurately capture the dynamic changes in cognitive load, a sliding time window analysis is performed on the collected physiological signals. Sliding time window analysis involves sliding a fixed-length time window across a continuous stream of physiological signal data, calculating corresponding statistical characteristics, such as mean, variance, or spectral features, within each time window. In this way, transient changes in physiological signals over short periods can be captured, changes that are often closely related to rapid fluctuations in cognitive load.

[0068] Similarly, the frequency and rate of change of the collected user actions are calculated within short time windows. For example, within time windows of a few seconds or tens of seconds, the number of mouse clicks, the number of characters entered on the keyboard, or the frequency of interface switching are calculated, and the rate of change of these frequencies is further calculated. This calculation helps to identify short-term changes in user actions; for example, the frequency of actions may decrease or the rate of change may increase as the task becomes more difficult.

[0069] This involves correlating instantaneous changes in physiological signals with short-term changes in operational behavior. This correlation analysis aims to discover synchronicity or causal relationships between physiological responses and behavioral performance. For example, when a dispatcher's heart rate momentarily increases, does their mouse click frequency simultaneously decrease, or does their operational hesitation time increase? Through the fusion analysis of multimodal data, a more comprehensive and accurate assessment of the dispatcher's cognitive load can be achieved.

[0070] When both transient changes in physiological signals and short-term changes in operational behavior indicate high load fluctuations—for example, when physiological signals show increased stress response while operational behavior exhibits decreased efficiency or increased errors—the system updates its cognitive load status. This dual-confirmation mechanism improves the accuracy and reliability of cognitive load assessment.

[0071] Finally, the system outputs a cognitive load level based on the updated cognitive load status. This level can be a quantified numerical value, such as a cognitive load index from 1 to 5, or a classification label, such as low load, medium load, or high load. The output of this level provides crucial information for subsequent decision-making actions and adjustments to scheduling schemes.

[0072] This application's solution, through comprehensive analysis of dispatchers' physiological signals and operational behaviors, enables a more complete and real-time perception of their cognitive load status. Basic cognitive load assessment methods may rely on data from only a single dimension, such as questionnaires or simple behavioral observations, making it difficult to capture the dynamics and complexity of cognitive load. This application, by collecting physiological signals, directly reflects the dispatcher's internal physiological state, such as stress levels and attention concentration; simultaneously, by collecting operational behaviors, it reflects the dispatcher's external performance in interacting with the system and task execution efficiency. By performing sliding time window analysis and calculating the frequency and rate of change within short time windows, this approach captures instantaneous and short-term fluctuations in cognitive load, rather than merely static average levels. More importantly, by correlating instantaneous changes in physiological signals with short-term changes in operational behaviors, and requiring both to simultaneously indicate high load fluctuations before updating the cognitive load status, this multimodal, multidimensional, and dynamically correlated analysis method effectively avoids misjudgments that may arise from a single data source, thereby improving the accuracy and robustness of cognitive load perception. This provides more reliable basic data for subsequent decision-making behavior labeling and deviation decision analysis.

[0073] Through the above technical solution, this application enables refined and real-time perception of the cognitive load status of dispatchers. Compared to methods relying solely on subjective reports or coarse behavioral observations, this solution combines the objectivity of physiological signals with the directness of operational behaviors, and significantly improves the accuracy and sensitivity of cognitive load assessment through dynamic analysis and multimodal data fusion. This precise cognitive load perception capability allows the system to more promptly identify potential stress or information overload situations faced by dispatchers, thus providing a more reliable basis for subsequent decision-making behavior labeling. For example, when a dispatcher is under high cognitive load, the accuracy of labeling their decision-making behavior will be greatly improved, helping the system to more accurately identify potential deviations in decision-making under stress, and conduct targeted analysis and weight adjustments, ultimately optimizing the record of the dispatcher's historical selection preferences and decision-making patterns, and improving the intelligence and adaptability of the entire obstetric medical resource dispatching system.

[0074] In some of the above embodiments, the step of marking the scheduler's decision-making behavior when the cognitive load state reaches a preset threshold includes: Acquire historical cognitive load data of dispatchers, which includes the cognitive load levels of dispatchers in different situations and their corresponding physiological signals and operational behavior patterns. Based on historical cognitive load data, an individualized cognitive load baseline for dispatchers is constructed, which reflects the routine cognitive load level of dispatchers in different situations. When sensing the cognitive load status of the scheduler in real time, the real-time cognitive load status is compared with the individualized cognitive load baseline. When the real-time cognitive load status deviates significantly from the individualized cognitive load baseline, and the direction of deviation indicates a high load, the preset threshold is dynamically adjusted. The dispatcher's decision-making behavior is marked based on the adjusted preset threshold.

[0075] Historical cognitive load data refers to the long-term collection and storage of cognitive load information for specific dispatchers in different work scenarios (e.g., handling routine tasks, responding to emergencies, and performing complex coordination). This data can originate from physiological signals (such as heart rate variability, skin conductance response, and eye movement data) and human-computer interaction behaviors (such as mouse click frequency, keyboard input speed, and interface switching frequency), and is analyzed by professional algorithms to form different cognitive load levels. The individualized cognitive load baseline is a personalized reference standard established for each dispatcher based on this historical data through statistical analysis or machine learning models. It reflects the dispatcher's typical cognitive load range and pattern in specific situations. For example, a dispatcher's cognitive load typically fluctuates at a low level when handling routine tasks; while in emergency situations, their cognitive load naturally increases, but remains within their normal emergency response load range. Real-time perception of the dispatcher's cognitive load status refers to the system continuously monitoring the dispatcher's current physiological signals and operational behaviors, and calculating their current cognitive load level in real time. Comparing the real-time cognitive load status with the individualized cognitive load baseline aims to identify whether the current state deviates from the dispatcher's typical load level in similar situations. A significant deviation, with the direction of deviation indicating high load, means that the current cognitive load not only exceeds the normal range but is also trending towards even higher loads. This may indicate that the dispatcher is facing unusual stress or challenges. In this situation, the system will dynamically adjust the preset threshold to better reflect the dispatcher's actual cognitive load, thereby more accurately determining when to flag their decision-making behavior.

[0076] This application's solution addresses the limitation of fixed thresholds in adapting to individual differences and changing circumstances by introducing an individualized cognitive load baseline for dispatchers and dynamically adjusting the preset threshold for decision-making behavior labeling based on a comparison between the real-time cognitive load status and this baseline. Specifically, when a dispatcher's real-time cognitive load status deviates significantly from their individualized baseline, indicating high load, the system can identify this as an abnormal or high-pressure state and adjust the labeling threshold accordingly. Thus, a dispatcher's behavior is only labeled when they are truly under pressure exceeding their normal load level, ensuring the accuracy and relevance of the labeling.

[0077] The above technical solution significantly improves the accuracy of dispatcher decision-making behavior labeling, avoiding misjudgments or omissions caused by fixed thresholds. This method better adapts to individual differences among dispatchers and the cognitive load fluctuations of the same dispatcher in different situations, making the recorded historical selection preferences and decision-making patterns more realistic and effective. This not only helps to more accurately analyze the decision-making characteristics of dispatchers under pressure but also provides high-quality data support for subsequent system optimization, personnel training, and risk assessment, thereby improving the overall intelligence level and security of obstetric medical resource scheduling.

[0078] In some of the above embodiments, the step of marking the scheduler's decision-making behavior when the cognitive load state reaches a preset threshold includes: Acquire physiological signals and operational behavior data of dispatchers when handling different task types, including equipment allocation, personnel mobilization, or site upgrades. Based on physiological signals and operational behavior data, identify cognitive load characteristics associated with different task types; The cognitive load characteristics are matched with the preset cognitive load source patterns to distinguish whether the cognitive load mainly comes from information overload, time pressure or task complexity. Based on the cognitive load source pattern, the scheduler's decision-making behavior is labeled, and the label includes the type of cognitive load source.

[0079] Specifically, acquiring physiological signals and operational behavior data of dispatchers when handling different task types refers to collecting, in real time, the dispatcher's physiological responses (e.g., heart rate, skin conductance, eye movement, EEG) and operational behaviors on the human-computer interface (e.g., mouse clicks, keyboard input, gaze focus area, operation duration) during specific tasks such as equipment allocation, personnel mobilization, or site upgrades, through sensors or system logs. This data is considered raw input reflecting the dispatcher's cognitive state. Task type can be understood as the various specific sub-tasks that the dispatcher needs to handle in a maternity emergency scenario, serving to provide task context for subsequent analysis.

[0080] Based on the aforementioned physiological signals and operational behavior data, cognitive load characteristics associated with different task types are identified. This typically involves preprocessing and feature extraction of the raw data, such as calculating heart rate variability, eye fixation density, operation frequency, or error rate. These characteristics quantify the scheduler's cognitive engagement and stress level in specific task situations. Cognitive load characteristics can be understood as quantitative indicators extracted from raw physiological and behavioral data that reflect cognitive load status; their purpose is to transform complex raw data into analyzable features.

[0081] The aforementioned cognitive load characteristics are matched with preset cognitive load source patterns to distinguish whether the cognitive load primarily stems from information overload, time pressure, or task complexity. These preset cognitive load source patterns are constructed based on extensive historical data and expert knowledge. Each pattern corresponds to a primary source of cognitive load and includes its typical combination of physiological and behavioral characteristics. For example, information overload may manifest as frequent eye movement and decreased information processing speed; time pressure may manifest as faster decision-making and increased error rates; and task complexity may manifest as prolonged focus and pauses in thinking. Through machine learning algorithms or rule matching, the real-time identified cognitive load characteristics are compared with these preset patterns to determine the primary source of the current cognitive load. The aim is to conduct a deeper attribution analysis of cognitive load.

[0082] Finally, based on the aforementioned cognitive load source patterns, the scheduler's decision-making behavior is tagged, with the tag indicating the type of cognitive load source. This means that when a scheduler makes a decision, in addition to recording its cognitive load level, the main cause of the high load is also recorded. For example, a decision might be tagged as high cognitive load - information overload or high cognitive load - time pressure. The purpose is to provide more refined contextual information for subsequent decision analysis and system optimization.

[0083] This application acquires physiological signals and operational behavior data of schedulers when handling different task types, and identifies cognitive load characteristics related to task types based on this data. This allows the system to match cognitive load characteristics with preset cognitive load source patterns. Thus, the system can accurately distinguish whether the scheduler's cognitive load primarily stems from information overload, time pressure, or task complexity. This nuanced distinction enables the system to not only record that decisions were made under high cognitive load when labeling scheduler decision-making behavior, but also to identify the specific reasons leading to the high load. This provides richer background information for subsequent analysis of the execution effects and clinical outcomes of deviations from decisions, allowing the system to more accurately understand the rationality or potential risks of decisions and adjust the weights of historical selection preferences and decision-making patterns accordingly. For example, the weight adjustment strategy for a suboptimal decision made under high time pressure may differ from that of a suboptimal decision made under information overload.

[0084] Through the aforementioned technical solution, this application enables more insightful labeling of dispatcher decision-making behavior. This labeling not only quantifies the degree of cognitive load but, more importantly, reveals the intrinsic driving factors of cognitive load. This allows the system to more accurately assess the background and potential impact of decisions when analyzing dispatchers' deviations, thus avoiding generalizing all decisions under high load. For example, a rapid decision made under extreme time pressure, even if the outcome is not optimal, may be understood by the system as a reasonable coping strategy rather than a simple erroneous decision. This refined identification of cognitive load sources greatly improves the accuracy and robustness of the system's learning of dispatcher decision-making patterns, enabling subsequent recommended alternatives to better fit the dispatcher's actual work context and cognitive characteristics, thereby effectively improving the intelligence level of obstetric medical resource scheduling and the effectiveness of decision support.

[0085] In some of the above implementation methods, the steps for analyzing the effects of deviations from decision-making and clinical outcomes include: Obtain key event logs during the deviation decision execution process. Key event logs include equipment arrival time, personnel response time, key operation completion time, and changes in patient vital signs. Obtain clinical outcome data for patients who deviate from the decision, including maternal and infant prognostic scores, complication rates, or length of hospital stay. Obtain patient status data before and after the implementation of the deviation decision. The patient status data includes physiological parameters, imaging examination results, or laboratory test results. Obtain the medical team's intervention records during the deviation from the decision-making process. The intervention records include temporary adjustments to the plan, additional resource inputs, or expert consultation opinions. By comparing changes in patient condition before and after the implementation, and combining this with the medical team's intervention records, we can analyze the actual impact of the deviation from the decision on the patient's condition and distinguish between the role of the decision itself and the role of external intervention. Correlation analysis was performed between key event logs and clinical outcome data to assess the direct implementation effects of deviations from decisions and the final clinical outcomes.

[0086] Specifically, acquiring critical event logs during the execution of deviation decisions refers to the automatic or manual recording by the system of key time points and events related to the decision after its execution. For example, equipment arrival time refers to the time it takes for specific medical equipment to be delivered and ready; personnel response time refers to the time it takes for relevant medical personnel to receive instructions and arrive at the scene; critical operation completion time refers to the completion time of important medical procedures such as the start of surgery and drug injection during emergency treatment; and changes in patient vital signs refer to the dynamic changes in physiological indicators such as heart rate, blood pressure, respiration, and blood oxygen saturation during the decision execution process. This log data provides an objective basis for evaluating the immediate efficiency and process quality of decision execution.

[0087] Obtaining patient clinical outcome data corresponding to deviations from the decision can be understood as collecting data on the final health status and treatment outcomes of patients directly related to that decision. For example, maternal and infant prognostic scores can use standards such as the Apgar score and neonatal asphyxia score; complication rate refers to the proportion of adverse events occurring during or after treatment; length of hospital stay refers to the total number of days from admission to discharge. These data are key indicators for measuring the long-term effects of the decision and the degree of patient benefit.

[0088] Obtaining patient status data before and after the implementation of a deviation decision specifically refers to a comprehensive assessment and recording of the patient's physiological condition before and after the implementation of the deviation decision. For example, physiological parameters include basic vital signs such as body temperature, pulse, respiration, and blood pressure; imaging examination results can include image data from ultrasound, CT, and MRI to assess organ function or disease conditions; and laboratory test results cover various test data such as complete blood count, biochemical indicators, and coagulation function. By comparing these data, the direct impact of the decision on the patient's physiological state can be quantified.

[0089] Obtaining intervention records from the healthcare team during the implementation of deviation decisions refers to collecting additional measures taken by healthcare professionals to address emergencies or optimize treatment processes during the implementation of deviation decisions. For example, temporary adjustments may include modifications to the original treatment plan; additional resource allocation may refer to the emergency deployment of extra equipment or personnel; and expert consultation opinions record the professional guidance and recommendations from senior physicians. These records help distinguish between the effectiveness of the decision itself and the impact of external interventions on the outcome.

[0090] Therefore, by comparing changes in patient condition before and after implementation, and combining this with the medical team's intervention records, the actual impact of deviations from the decision on patient condition can be analyzed, and the roles of the decision itself and external interventions can be distinguished. This means that when evaluating the effectiveness of a decision, it is necessary to attribute the improvement or deterioration of patient condition to the decision itself, while also considering whether the medical team's active intervention had a corrective effect on the outcome. For example, if the patient's condition improves after the decision is implemented, but at the same time, an expert consultation is conducted and the treatment plan is adjusted, it is necessary to analyze whether this improvement mainly stems from the original decision or the adjustments made after the consultation.

[0091] Finally, a correlation analysis is performed between the critical event logs and clinical outcome data to assess the direct implementation effects of deviations from the decision and the final clinical outcome. This means comprehensively considering the efficiency and quality of the decision implementation process (reflected in the critical event logs) with the final patient health outcome (reflected in the clinical outcome data). For example, if the equipment arrival time is too long but the final clinical outcome is good, it may be necessary to analyze whether other factors compensated for the impact of the equipment delay, or whether the delay did not have a decisive impact on the final outcome.

[0092] This application addresses potential biases and inaccuracies through multi-dimensional and refined data collection and analysis. First, by acquiring key event logs, the execution process of deviations from decisions can be recorded in real-time and objectively, thereby capturing the efficiency and potential problems of the decision at the practical operational level. Second, patient clinical outcome data and patient status data before and after execution provide direct evidence of the decision's impact on patient health, enabling the evaluation of decision effectiveness from both macro and micro perspectives. More importantly, by incorporating intervention records from the medical team, this application can effectively distinguish between the effectiveness of the decision itself and the corrective effect of external interventions on the outcome, avoiding the erroneous attribution of external factors to the decision itself, thus improving the accuracy and objectivity of the analysis. Finally, by correlating process data (key event logs) with outcome data (clinical outcome data), the evaluation of deviations from decisions is no longer isolated but forms a complete closed loop from execution to outcome, contributing to a comprehensive understanding of the profound impact of decisions.

[0093] Through the aforementioned technical solution, this application enables a more comprehensive, in-depth, and objective evaluation of dispatcher deviation decisions. Compared to analysis based solely on experience or a single indicator, this solution integrates multi-source heterogeneous data, including key event logs, patient clinical outcome data, patient status data, and medical team intervention records. This allows for a more accurate identification of the actual impact of deviation decisions and an effective distinction between the decision itself and the role of external interventions in the outcome. This not only helps in accurately assessing the value of deviation decisions—for example, identifying innovative decisions that, while deviating from the norm, yield better results in specific high-load situations—but also reveals decisions that appear effective but actually rely on external interventions for success. This refined analytical capability significantly improves the quality of learning and optimizing dispatcher decision-making patterns, providing more reliable data support for subsequent intelligent recommendations and dispatcher training, thereby continuously improving the efficiency of medical resource allocation and patient prognosis in obstetric emergency scenarios.

[0094] Based on the same inventive concept, this application also discloses an obstetric medical resource scheduling system, such as... Figure 2 As shown, the system includes: Status information acquisition module 1 is used to acquire detailed status information of obstetric medical equipment. The detailed status information includes the preparation process information of the equipment from non-ready state to ready state. Personnel information acquisition module 2 is used to acquire the real-time location information and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. The process preset module 3 is used to preset the resource combination process for obstetric emergency scenarios. The resource combination process includes multiple task steps. The time calculation module 4 is used to determine the estimated time for each task step in the resource combination process based on refined status information, real-time location information and task information, and to calculate the estimated completion time of the resource combination process based on the estimated time for each task step. The scheme generation module 5 is used to generate a preliminary resource scheduling scheme; The simulation verification module 6 is used to simulate the preliminary resource scheduling scheme based on refined status information, real-time location information, task information and the estimated completion time of the resource combination process, so as to identify resource status conflicts, time conflicts or personnel response capability conflicts in the preliminary resource scheduling scheme. The scheme adjustment module 7 is used to adjust the preliminary resource scheduling scheme or generate alternative schemes based on the identified conflicts, and generate the final resource scheduling instruction when the simulation results show no conflict or the conflict has been resolved. The instruction issuance module 8 is used to issue the final resource scheduling instructions to the relevant personnel.

[0095] This application constructs a system that integrates refined status information acquisition, real-time personnel information perception, emergency procedure pre-setting, dynamic time calculation, plan generation and simulation verification, and intelligent adjustment and instruction issuance functions. This system can comprehensively and in real time grasp the real status of obstetric medical resources and personnel dynamics, thereby effectively identifying potential resource conflicts in obstetric emergency scenarios and providing optimized or alternative scheduling solutions.

[0096] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for allocating obstetric medical resources, characterized in that, include: Acquire detailed status information of obstetric medical equipment, including information on the preparation process for the equipment to transition from a non-ready state to a ready state; Obtain real-time location and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. A pre-defined resource combination process for obstetric emergency scenarios, which includes multiple task steps; Based on refined status information, real-time location information of personnel, and task information, the estimated time for each task step in the resource combination process is determined, and the estimated completion time of the resource combination process is calculated based on the estimated time for each task step. Generate a preliminary resource scheduling plan; Based on refined status information, real-time location information of personnel, task information, and the estimated completion time of resource combination process, a preliminary resource scheduling plan is simulated to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling plan. Based on the identified conflicts, the initial resource scheduling plan is adjusted or an alternative plan is generated, and the final resource scheduling instruction is generated if the simulation results show no conflict or the conflict has been resolved. The final resource scheduling instructions will be issued to the relevant personnel.

2. The method for allocating obstetric medical resources according to claim 1, characterized in that, The step of simulating the preliminary resource scheduling scheme based on refined status information, real-time location information of personnel, task information, and the estimated completion time of the resource combination process, in order to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling scheme, further includes: Acquire parameter information of the microenvironment in which the high-precision medical device is located, including temperature, humidity or vibration; Based on parameter information and the pre-set environmental sensitivity curve inside the high-precision medical device, calculate the additional preparation time required for the advanced functions of the high-precision medical device. The additional preparation time is added to the basic preparation time of the high-precision medical equipment to obtain the expected functional readiness time of the high-precision medical equipment. Based on the expected functional readiness time, determine whether the advanced functions of high-precision medical equipment can be activated in time as required by the initial resource scheduling plan. If higher-level functions cannot be activated in time as required by the initial resource scheduling scheme, a higher-level function readiness conflict is identified.

3. The method for allocating obstetric medical resources according to claim 1, characterized in that, The step of adjusting the preliminary resource scheduling scheme or generating an alternative scheme based on the identified conflicts, and generating the final resource scheduling instruction when the simulation results show no conflicts or the conflicts have been resolved, further includes: Generate a summary view containing multiple alternatives. The summary view highlights the estimated readiness time for each alternative, the actual arrival time of the required critical equipment and personnel, and potential minor risk warnings. Based on the pre-set obstetric emergency priority rules, a preliminary risk assessment is conducted for each alternative, and the risk assessment results are displayed in the summary view using color coding or risk level marking. Provides an interactive timeline view that shows the parallel and serial relationships of tasks in each alternative, as well as key milestone dates; In response to receiving a dispatcher's instruction to select one of multiple alternatives, a partial simulation of that alternative is performed in the virtual emergency rescue sandbox; Record the dispatcher's historical selection preferences and decision-making patterns; Based on historical selection preferences and decision-making patterns, alternatives that align with the scheduler's preferences or have been successfully adopted in similar situations are given priority.

4. The method for allocating obstetric medical resources according to claim 3, characterized in that, The step of generating a summary view containing multiple alternatives, highlighting the estimated readiness time for each alternative, the actual arrival time of required critical equipment and personnel, and potential secondary risks, further includes: The system senses the scheduler's interaction with the summary view, including the scheduler's focus area, interaction duration, or click or hover actions on specific information elements. Dynamically adjust the presentation or level of detail of information in the summary view based on interactive behavior; When the focus area is on the estimated readiness time for an extended period of time, the parallel and serial relationships of key tasks in the alternative solution or the estimated time of each task are overlaid. When the interaction involves clicking or hovering over a minor risk warning, a risk details window pops up, showing the clinical impact, probability of occurrence, or urgency of the risk. The density of information in the summary view is dynamically adjusted based on the dispatcher's perceived load status. When cognitive load is high, the information density in the simplified summary view is reduced to show only the estimated readiness time, the actual arrival time of the required critical equipment and personnel, and secondary risks are highlighted with icons. When cognitive load is moderate, expand the density of information in the summary view to display more detailed information.

5. The method for allocating obstetric medical resources according to claim 3, characterized in that, The steps for recording the dispatcher's historical selection preferences and decision-making patterns include: Perceive the cognitive load status of the dispatcher; When the cognitive load reaches a preset threshold, the scheduler's decision-making behavior is flagged; By comparing the decision-making behavior of the marked individuals with the dispatcher's typical decision-making patterns, deviations from the established decision-making process can be identified. Analyze the effects of deviations from the decision-making process on clinical outcomes; Adjust the weight of deviations from the decision in historical choice preferences and decision-making patterns based on the implementation effect and clinical results.

6. The method for scheduling obstetric medical resources according to claim 5, characterized in that, The steps for perceiving the cognitive load status of the scheduler include: Collect the dispatcher's physiological signals; Data collection and dispatching personnel's operational behavior on the human-computer interaction interface; Sliding time window analysis is performed on physiological signals to capture instantaneous changes in physiological signals; Calculate the frequency and rate of change of operational behavior within a short time window to capture short-term changes in operational behavior; Correlating instantaneous changes in physiological signals with short-term changes in operational behavior; When both transient changes in physiological signals and short-term changes in operational behavior indicate high workload fluctuations, update the cognitive workload status. Output the level of cognitive load based on the updated cognitive load status.

7. The method for allocating obstetric medical resources according to claim 5, characterized in that, The step of marking the scheduler's decision-making behavior when the cognitive load reaches a preset threshold includes: Acquire historical cognitive load data of dispatchers, which includes the cognitive load levels of dispatchers in different situations and their corresponding physiological signals and operational behavior patterns. Based on historical cognitive load data, an individualized cognitive load baseline for dispatchers is constructed, which reflects the routine cognitive load level of dispatchers in different situations. When sensing the cognitive load status of the scheduler in real time, the real-time cognitive load status is compared with the individualized cognitive load baseline. When the real-time cognitive load status deviates significantly from the individualized cognitive load baseline, and the direction of deviation indicates a high load, the preset threshold is dynamically adjusted. The dispatcher's decision-making behavior is marked based on the adjusted preset threshold.

8. The method for scheduling obstetric medical resources according to claim 5, characterized in that, The step of marking the scheduler's decision-making behavior when the cognitive load reaches a preset threshold includes: Acquire physiological signals and operational behavior data of dispatchers when handling different task types, including equipment allocation, personnel mobilization, or site upgrades. Based on physiological signals and operational behavior data, identify cognitive load characteristics associated with different task types; The cognitive load characteristics are matched with the preset cognitive load source patterns to distinguish whether the cognitive load mainly comes from information overload, time pressure or task complexity. Based on the cognitive load source pattern, the scheduler's decision-making behavior is labeled, and the label includes the type of cognitive load source.

9. The method for scheduling obstetric medical resources according to claim 5, characterized in that, The steps for analyzing the effects of deviations from decision-making on implementation and clinical outcomes include: Obtain key event logs during the deviation decision execution process. Key event logs include equipment arrival time, personnel response time, key operation completion time, and changes in patient vital signs. Obtain clinical outcome data for patients who deviate from the decision, including maternal and infant prognostic scores, complication rates, or length of hospital stay. Obtain patient status data before and after the implementation of the deviation decision. The patient status data includes physiological parameters, imaging examination results, or laboratory test results. Obtain the medical team's intervention records during the deviation from the decision-making process. The intervention records include temporary adjustments to the plan, additional resource inputs, or expert consultation opinions. By comparing changes in patient condition before and after the implementation, and combining this with the medical team's intervention records, we can analyze the actual impact of the deviation from the decision on the patient's condition and distinguish between the role of the decision itself and the role of external intervention. Correlation analysis was performed between key event logs and clinical outcome data to assess the direct implementation effects of deviations from decisions and the final clinical outcomes.

10. A system for scheduling obstetric medical resources, characterized in that, The system includes: The status information acquisition module is used to acquire detailed status information of obstetric medical equipment. The detailed status information includes the preparation process information of the equipment from non-ready state to ready state. The personnel information acquisition module is used to acquire the real-time location information and task information of key personnel in the obstetrics department. The task information includes the estimated completion time of the personnel's current task. The process preset module is used to preset the resource combination process for obstetric emergency scenarios. The resource combination process includes multiple task steps. The time calculation module is used to determine the estimated time for each task step in the resource combination process based on refined status information, real-time location information of personnel, and task information, and to calculate the estimated completion time of the resource combination process based on the estimated time for each task step. The scheme generation module is used to generate preliminary resource scheduling schemes; The simulation and verification module is used to simulate the preliminary resource scheduling scheme based on refined status information, real-time location information of personnel, task information, and the estimated completion time of the resource combination process, so as to identify resource status conflicts, time conflicts, or personnel response capability conflicts in the preliminary resource scheduling scheme. The scheme adjustment module is used to adjust the initial resource scheduling scheme or generate alternative schemes based on the identified conflicts, and generate the final resource scheduling instructions when the simulation results show no conflict or the conflict has been resolved. The instruction issuance module is used to issue the final resource scheduling instructions to the relevant personnel.

Images