A medical care staff work efficiency quantification method and system based on multi-dimensional data
By constructing the ward information entropy field and phase space reconstruction, and combining it with cross-scale causal emergence recognition, the real-time and multi-dimensional problems of medical and nursing staff work efficiency assessment in existing technologies have been solved, and the accurate quantification and real-time management of medical and nursing staff work efficiency have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIN HUA HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
- Filing Date
- 2026-03-04
- Publication Date
- 2026-06-02
Smart Images
Figure CN122135907A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of efficiency quantification technology, specifically relating to a method and system for quantifying the work efficiency of medical caregivers based on multidimensional data. Background Technology
[0002] Current assessments of healthcare worker performance largely rely on traditional methods such as work hour statistics, task completion counts, supervisor subjective evaluations, or patient satisfaction surveys. While these methods reflect work output to some extent, they have significant limitations: First, they neglect environmental complexity and fail to incorporate dynamic ward needs (such as call frequency and distribution of critically ill patients) into the assessment system. Second, they ignore individual physiological and psychological states, failing to identify performance declines under fatigue, stress, or cognitive overload. Third, assessments are often delayed and one-sided, with most evaluations being post-hoc summaries lacking real-time and predictive capabilities. Fourth, they struggle to quantify implicit work, such as emotional labor, multitasking, and orderly behaviors like emergency response. Existing research, while attempting to introduce wearable devices to monitor activity-related physiological indicators like heart rate variability (HRV) and skin conductance, or to analyze mobility efficiency using location data, largely remains at a single-dimensional level. They fail to construct a cross-scale collaborative assessment model encompassing "environment-individual-behavior," leading to discrepancies between assessment results and actual workload and performance, thus hindering accurate support for real-time scheduling, personalized training, and health interventions. Summary of the Invention
[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for quantifying the work efficiency of medical caregivers based on multidimensional data.
[0004] The objective of this invention can be achieved through the following technical solutions: A method for quantifying the work efficiency of medical caregivers based on multidimensional data, the implementation of which includes the following steps: Step S1: Obtain historical data stream, which includes the historical location coordinates and historical event markers of medical caregivers. Construct a ward information entropy field based on the historical data stream to obtain the location demand entropy. Step S2: Continuously collect real-time data streams, which include the real-time location coordinates of the medical caregiver, real-time event markers, and real-time physiological signals. Based on the real-time data streams and the location demand entropy, perform negative entropy assessment and output the real-time negative entropy flow trajectory. Step S3: Reconstruct the phase space based on the real-time data stream to obtain the real-time control margin trajectory; Step S4: Perform cross-scale causal emergence identification based on the real-time data stream and output the real-time causal emergence intensity trajectory; Step S5: Optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.
[0005] Preferably, the construction of the ward information entropy field in step S1 specifically involves: The ward floor plan is divided into grids and each grid is assigned a unique number; Input the historical location coordinates and the historical event markers; In the historical data stream, all events that occur within the grid are statistically analyzed, and the probability of each event type occurring in that grid is calculated. The probability of each event type occurring in that grid is then substituted into the information entropy formula to obtain the event occurrence rate entropy of that grid. The percentage of total time that all medical caregivers' trajectory points fall on a single grid in the historical data stream is recorded as the occurrence probability. The entropy value of the occurrence probability is obtained as the trajectory uncertainty entropy. The location demand entropy of the grid is obtained by weighted fusion of the event occurrence rate entropy and the trajectory uncertainty entropy. .
[0006] Preferably, the negative entropy evaluation in step S2 specifically includes: The location of the medical care worker is determined based on the real-time location coordinates, and the location demand entropy of the grid is read as the exposure entropy. The ordered gain is defined mathematically as follows: ,in, For a moment , grid Ordering gain at the location, This is the global gain adjustment coefficient. The inherent information value of event type k, For grid Location demand entropy; The real-time negative entropy stream is obtained based on the exposure entropy and the ordering gain, mathematically described as follows: ,in, The real-time negative entropy flow at time t. This is the real-time negative entropy flow from the previous moment. This is an indicator function that returns 1 when an event completes at time t, and 0 otherwise. The attenuation coefficient is... Let be the exposure entropy at time t; The real-time negative entropy flow trajectory is obtained based on the real-time negative entropy flow.
[0007] Preferably, the phase space reconstruction in step S3 specifically includes: Extract a segment of HRV time series with a preset time delay. With an embedding dimension m, a one-dimensional HRV time series is reconstructed into a series of points in an m-dimensional phase space; The center of phase space is obtained, which is the arithmetic mean of the points in phase space. The distance from each point to the center is calculated to obtain the average distance and the standard deviation of the distance in phase space. The real-time control margin is calculated and mathematically described as follows: ,in, The real-time control margin at time t. The average distance, This represents the distance from the standard deviation. The real-time control margin trajectory is obtained based on the real-time control margin.
[0008] Preferably, the cross-scale causal emergence identification in step S4 specifically includes: The real-time location coordinates and the real-time event markers are automatically clustered into the macro-level behavioral state of the medical caregivers; The microphysiological indicators of the medical caregiver are obtained based on the real-time physiological signals. The microscopic physiological indicators and the macroscopic behavioral state are discretized to obtain the transfer entropy from the microscopic physiological indicators to the macroscopic behavioral state, mathematically described as follows: ,in, Let be the transfer entropy from the microscopic physiological index P to the macroscopic behavioral state B at time t. For probability, for Macro-level behavioral state at any given moment Let k be the past k values of the macroscopic behavioral state at time t. These are the past l values of the microphysiological indicators at time t; The propagation entropy from the macroscopic behavioral state to its own future is obtained; The real-time causal emergence intensity is obtained based on the propagation entropy, mathematically described as follows: ,in, Let be the real-time causal emergence intensity at time t. The transfer entropy from the macroscopic behavioral state to its own future. Let N be the transfer entropy from the i-th microphysiological indicator to the macrobehavioral state, and N be the number of samples. The real-time causal emergence intensity trajectory is obtained based on the real-time causal emergence intensity.
[0009] Preferably, the strategy optimization in step S5 specifically involves: The real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory constitute a three-dimensional state space. By analyzing historical performance shift data, performance regions are divided in the three-dimensional state space. Project the current status point of the medical caregiver onto the three-dimensional status space to determine the effectiveness zone; It has a built-in rule model that outputs forward-looking optimization suggestions; The output of the comprehensive performance report includes visualization charts of the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, performance area labels for key periods, and forward-looking optimization suggestions.
[0010] A system for quantifying the work efficiency of medical caregivers based on multidimensional data, used to execute the aforementioned method for quantifying the work efficiency of medical caregivers based on multidimensional data, includes an information entropy field construction module, a negative entropy evaluation module, a phase space reconstruction module, a causal emergence identification module, and a strategy optimization module. The information entropy field construction module is used to acquire historical data streams, which include the historical location coordinates of medical caregivers and historical event markers. Based on the historical data streams, a ward information entropy field is constructed to obtain the location demand entropy. The negative entropy assessment module is used to continuously collect real-time data streams, which include the real-time location coordinates of medical caregivers, real-time event markers, and real-time physiological signals. Based on the real-time data streams and the location demand entropy, negative entropy assessment is performed, and the real-time negative entropy flow trajectory is output. The phase space reconstruction module is used to reconstruct the phase space based on the real-time data stream to obtain the real-time control margin trajectory. The causal emergence identification module is used to perform cross-scale causal emergence identification based on the real-time data stream and output the real-time causal emergence intensity trajectory. The strategy optimization module is used to optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.
[0011] The beneficial effects of this invention are as follows: (1) By modeling the entropy field, the dynamic needs of the ward can be visualized, and the environment can be intelligently perceived, so that management work can be shifted from experience-driven to data-driven.
[0012] (2) By reconstructing phase space and identifying causal emergence, the physiological resilience and cognitive dominance of caregivers can be accurately identified, and fatigue and stress can be warned in advance, so as to realize real-time monitoring of individual status.
[0013] (3) Through three-dimensional state space classification and rule model, provide managers with a scientific basis for intervention.
[0014] (4) Through negative entropy flow tracking and optimization, not only can individual efficiency be improved, but it can also be used for ward scheduling, task allocation and process reengineering, ultimately achieving a synergistic improvement in nursing quality, employee health and operational efficiency. Attached Figure Description
[0015] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.
[0016] Figure 1 This is a flowchart illustrating the steps of a method for quantifying the work efficiency of medical caregivers based on multidimensional data, according to the present invention. Detailed Implementation
[0017] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.
[0018] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.
[0019] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.
[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.
[0021] Example 1: Please see Figure 1 A method for quantifying the work efficiency of medical caregivers based on multidimensional data, comprising: Step S1: Obtain historical data streams through the hospital information system. The historical data streams include the historical location coordinates of medical caregivers and historical event markers (historical discrete events from HIS, such as [timestamp, event type, associated bed]). Construct a ward information entropy field based on the historical data streams to obtain the location demand entropy. Step S2: Continuously collect real-time data streams through wearable devices (smart bracelets, work badges, etc.) and the hospital information system. The real-time data streams include the real-time location coordinates, real-time event markers, and real-time physiological signals of the medical caregivers. Based on the real-time data streams and the location demand entropy, perform negative entropy assessment (quantify how much environmental uncertainty a specific medical caregiver actually handles in a specific shift) and output the real-time negative entropy flow trajectory. Step S3: Based on the real-time data stream, perform phase space reconstruction to quantify the stability and resilience of the medical caregiver's own physiological and psychological system under the current work pressure, and obtain the real-time control margin trajectory. Step S4: Based on the real-time data stream, perform cross-scale causal emergence recognition to determine whether the caregiver's work is dominated by higher cognition or driven by lower physiological responses, and output the real-time causal emergence intensity trajectory. Step S5: Optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.
[0022] In this embodiment, the construction of the ward information entropy field is specifically as follows: S101: Divide the ward floor plan into multiple grids and assign a unique number to each grid; S102: Input the historical location coordinates and historical event markers of all healthcare workers over a past period; S103: Statistically analyze all events occurring within the grid in the historical data stream and calculate the probability of each event type (such as calling, feeding, bathing) occurring in that grid. Substitute these probabilities into the information entropy formula to obtain the event occurrence rate entropy for that grid. For example, in the nurse station grid, the event type is mainly paperwork with a high probability, while other events have low probabilities, resulting in a lower calculated event occurrence rate entropy (low uncertainty). However, in a critical care patient bed grid, multiple events such as calling and emergency treatment may occur frequently with similar probabilities, resulting in a high calculated event occurrence rate entropy (high uncertainty). S104: Calculate the percentage of time during which the trajectory points of all medical caregivers fall within a single grid in the historical data stream, denoted as the probability of occurrence. Obtain the entropy value of this probability of occurrence as the trajectory uncertainty entropy, mathematically described as... ,in, For grid trajectory uncertainty entropy, This represents the probability of occurrence; for example, the center of a corridor. Close to 0.5 (frequently worn), Very tall; a corner for storing miscellaneous items. Approaching 0 Very low; S105: The location demand entropy of the grid is obtained by weighted fusion of the event occurrence rate entropy and the trajectory uncertainty entropy. .
[0023] In this embodiment, the negative entropy evaluation specifically refers to: S201: Based on the real-time location coordinates, locate the grid where the medical care worker is located and read the location demand entropy of the grid as the exposure entropy (i.e., the uncertainty of the environment that the medical care worker is exposed to at that time). S202: Whenever a healthcare worker completes an event (such as responding to a call), it means that they have output an ordered action at that location, offsetting part of the disorder in the environment. Therefore, an ordering gain is defined, mathematically described as follows: ,in, For a moment , grid Ordering gain at the location, This is the global gain adjustment coefficient. The inherent information value of event type k (obtained through historical data, representing how much order the system can bring on average by processing one event of this type, for example, the order brought by a call response is much higher than that brought by a feeding operation). For grid Location demand entropy; S203: Based on the exposure entropy and the ordering gain, a real-time negative entropy stream is obtained, mathematically described as follows: ,in, The real-time negative entropy flow at time t. This is the real-time negative entropy flow from the previous moment. This is an indicator function that returns 1 when an event completes at time t, and 0 otherwise. The decay coefficient represents the amount of order lost per second due to exposure to an environment with a unit entropy value. Let t be the exposure entropy; the real-time negative entropy flow is a dynamic equilibrium, where healthcare workers are constantly exposed to entropy (consuming mental energy) and generate gains (creating order) by processing events. A decrease indicates that healthcare workers are not being able to keep up with the rate of exposure to environmental disorder, and the system is in disarray. An increase or a leveling off indicates that order has been effectively maintained or improved; S204: Obtain the real-time negative entropy flow trajectory based on the real-time negative entropy flow.
[0024] In this embodiment, the phase space reconstruction specifically refers to: S301: Extract a segment of HRV (Heart Rate Variability) time series and preset an appropriate time delay. With an embedding dimension m, a one-dimensional HRV time series {x1,x2,x3…} is reconstructed into a series of points in an m-dimensional phase space: X1=(x1,x2,x3…} ,…,x1+(m-1) ), X2=(x2,x2+ ) ,…,x²+(m-1) ), and so on; S302: Obtain the center of phase space, i.e. the arithmetic mean of the points in phase space, and calculate the distance from each point to the center to obtain the average distance and standard deviation of the distance in phase space; S303: The real-time control margin is calculated and mathematically described as follows: ,in, The real-time control margin at time t. The average distance, This represents the distance from the standard deviation. A high value indicates that the physiological system is in a stable and resilient state, and can effectively resist disturbances; A low value indicates a rigid phase space, insufficient or disordered variability, while excessive variability indicates decreased stability. S304: Obtain the real-time control margin trajectory based on the real-time control margin.
[0025] In this embodiment, the cross-scale causal emergence identification specifically refers to: S401: Automatically cluster the real-time location coordinates and the real-time event markers into the macro-behavioral status of medical caregivers (ward rounds, feeding, body bathing, etc.). S402: Based on the real-time physiological signals (such as low-frequency power, high-frequency power of HRV, skin conductance level, etc.), obtain the microphysiological indicators of the medical caregiver; S403: Discretize the continuous microscopic physiological indicators and the discrete macroscopic behavioral states (mapped to numbers) to obtain the transfer entropy from the microscopic physiological indicators to the macroscopic behavioral states, mathematically described as follows: ,in, Let t be the transfer entropy from the microphysiological index P to the macrobehavioral state B at time t (which measures the degree to which physiology drives or interferes with behavior). For probability, for Macro-level behavioral state at any given moment Let k be the past k values of the macroscopic behavioral state at time t. These are the past l values of the microphysiological index at time t. For macroscopic behavioral state in The value at time is And the state sequence at time t and its k past times is as follows: Simultaneously, the sequence of microphysiological indicators at time t and its l past times is... The joint probability, Given the past k macroscopic behavioral states And the past 1 microphysiological indicators Under the condition that, the state at the next moment is The probability, Given the past k macroscopic behavioral states Under the condition that, the state at the next moment is The probability of; S404: Obtain the transfer entropy from the macroscopic behavioral state to its own future (i.e. its self-predictability). S405: Based on the propagation entropy, the real-time causal emergence intensity is obtained, mathematically described as follows: ,in, Let be the real-time causal emergence intensity at time t. The transfer entropy from the macroscopic behavioral state to its own future. Let N be the transfer entropy from the i-th microphysiological indicator to the macroscopic behavioral state; if A value greater than 0 indicates that the intrinsic information flow (self-determination) of the behavioral pattern is greater than the sum of the influences of all physiological indicators, suggesting that the caregiver is in a state of seamless knowledge-action alignment, with behavior dominated by planning, habits, and experience (macro-cognition), resulting in high efficacy; if A value of 0 or less than 0 indicates that behavior is largely driven or interfered with by physiological responses (microstates) such as heart rate and skin conductance. This suggests that caregivers may be under stress, fatigued, or distracted, and their behavior is reactive and ineffective. S406: Obtain the real-time causal emergence intensity trajectory based on the real-time causal emergence intensity.
[0026] In this embodiment, the strategy optimization specifically includes: S501: The real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory constitute a three-dimensional state space. Through machine learning, the historical performance shift data is analyzed, and different performance regions (such as high robust smooth region, high efficiency dissipation region, and fragile response region) are divided in the three-dimensional state space. S502: Set the current status point of the medical caregiver ( , , Projected into the three-dimensional state space, the performance region is determined; such as Stable or rising, high, A positive value indicates the optimal state, placing it within the highly robust and smooth region. High but volatile. medium, The level is close to zero; at this point, healthcare workers are busy but their workload is manageable, and the system is in a highly efficient dissipation zone. Decline or sharp fluctuations Low, A negative value indicates a risky state, a vulnerable response zone, and requires intervention. S503: It has a built-in simple rule model that outputs forward-looking optimization suggestions. For example, when the state enters the vulnerable response zone, it simulates the predictive impact of different intervention measures (such as "suggest resting for 5 minutes" or "suggest handing over high-entropy tasks to colleagues") on the future trend of the three curves and selects the strategy that enables the state to return to the efficient dissipation zone or the highly robust smooth zone as the recommendation. S504: Output the comprehensive performance report, including visualization charts of the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, performance area labels for key periods, and forward-looking optimization suggestions, etc.
[0027] Example 2: A system for quantifying the work efficiency of medical caregivers based on multidimensional data includes an information entropy field construction module, a negative entropy evaluation module, a phase space reconstruction module, a causal emergence identification module, and a strategy optimization module. The information entropy field construction module is used to obtain historical data streams through the hospital information system. The historical data streams include the historical location coordinates of medical caregivers and historical event markers (historical discrete events from HIS, such as [timestamp, event type, associated bed]). Based on the historical data streams, the ward information entropy field is constructed to obtain the location demand entropy. The negative entropy assessment module is used to continuously collect real-time data streams through wearable devices (smart bracelets, name tags, etc.) and hospital information systems. The real-time data streams include the real-time location coordinates, real-time event markers, and real-time physiological signals of medical caregivers. Based on the real-time data streams and the location demand entropy, negative entropy assessment is performed (quantifying how much environmental uncertainty a specific medical caregiver actually handles in a specific shift), and the real-time negative entropy flow trajectory is output. The phase space reconstruction module is used to reconstruct the phase space based on the real-time data stream, quantify the stability and elasticity of the medical care worker's own physiological and psychological system under the current work pressure, and obtain the real-time control margin trajectory. The causal emergence recognition module is used to perform cross-scale causal emergence recognition based on the real-time data stream, determine whether the caregiver's work is dominated by higher cognition or driven by lower physiological responses, and output the real-time causal emergence intensity trajectory. The strategy optimization module is used to optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.
[0028] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. A method for quantifying the work efficiency of medical caregivers based on multidimensional data, characterized in that, Includes the following steps: Step S1: Obtain historical data stream, which includes the historical location coordinates and historical event markers of medical caregivers. Construct a ward information entropy field based on the historical data stream to obtain the location demand entropy. Step S2: Continuously collect real-time data streams, which include the real-time location coordinates of the medical caregiver, real-time event markers, and real-time physiological signals. Based on the real-time data streams and the location demand entropy, perform negative entropy assessment and output the real-time negative entropy flow trajectory. Step S3: Reconstruct the phase space based on the real-time data stream to obtain the real-time control margin trajectory; Step S4: Perform cross-scale causal emergence identification based on the real-time data stream and output the real-time causal emergence intensity trajectory; Step S5: Optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.
2. The method for quantifying the work efficiency of medical caregivers based on multidimensional data according to claim 1, characterized in that, The construction of the ward information entropy field in step S1 is specifically as follows: The ward floor plan is divided into grids and each grid is assigned a unique number; Input the historical location coordinates and the historical event markers; In the historical data stream, all events that occur within the grid are statistically analyzed, and the probability of each event type occurring in that grid is calculated. The probability of each event type occurring in that grid is then substituted into the information entropy formula to obtain the event occurrence rate entropy of that grid. The percentage of total time that all medical caregivers' trajectory points fall on a single grid in the historical data stream is recorded as the occurrence probability. The entropy value of the occurrence probability is obtained as the trajectory uncertainty entropy. The location demand entropy of the grid is obtained by weighted fusion of the event occurrence rate entropy and the trajectory uncertainty entropy. .
3. The method for quantifying the work efficiency of medical caregivers based on multidimensional data according to claim 1, characterized in that, The negative entropy evaluation in step S2 specifically refers to: The location of the medical care worker is determined based on the real-time location coordinates, and the location demand entropy of the grid is read as the exposure entropy. The ordered gain is defined mathematically as follows: ,in, For a moment , grid Ordering gain at the location, This is the global gain adjustment coefficient. The inherent information value of event type k, For grid Location demand entropy; The real-time negative entropy stream is obtained based on the exposure entropy and the ordering gain, mathematically described as follows: ,in, The real-time negative entropy flow at time t. This is the real-time negative entropy flow from the previous moment. This is an indicator function that returns 1 when an event completes at time t, and 0 otherwise. The attenuation coefficient is... Let be the exposure entropy at time t; The real-time negative entropy flow trajectory is obtained based on the real-time negative entropy flow.
4. The method for quantifying the work efficiency of medical caregivers based on multidimensional data according to claim 1, characterized in that, The phase space reconstruction in step S3 specifically refers to: Extract a segment of HRV time series with a preset time delay. With an embedding dimension m, a one-dimensional HRV time series is reconstructed into a series of points in an m-dimensional phase space; The center of phase space is obtained, which is the arithmetic mean of the points in phase space. The distance from each point to the center is calculated to obtain the average distance and the standard deviation of the distance in phase space. The real-time control margin is calculated and mathematically described as follows: ,in, The real-time control margin at time t. The average distance, This represents the distance from the standard deviation. The real-time control margin trajectory is obtained based on the real-time control margin.
5. The method for quantifying the work efficiency of medical caregivers based on multidimensional data according to claim 1, characterized in that, The cross-scale causal emergence identification in step S4 specifically refers to: The real-time location coordinates and the real-time event markers are automatically clustered into the macro-level behavioral state of the medical caregivers; The microphysiological indicators of the medical caregiver are obtained based on the real-time physiological signals. The microscopic physiological indicators and the macroscopic behavioral state are discretized to obtain the transfer entropy from the microscopic physiological indicators to the macroscopic behavioral state, mathematically described as follows: ,in, Let be the transfer entropy from the microscopic physiological index P to the macroscopic behavioral state B at time t. For probability, for Macro-level behavioral state at any given moment Let k be the past k values of the macroscopic behavioral state at time t. These are the past l values of the microphysiological indicators at time t; The propagation entropy from the macroscopic behavioral state to its own future is obtained; The real-time causal emergence intensity is obtained based on the propagation entropy, mathematically described as follows: ,in, Let be the real-time causal emergence intensity at time t. The transfer entropy from the macroscopic behavioral state to its own future. Let N be the transfer entropy from the i-th microphysiological indicator to the macrobehavioral state, and N be the number of samples. The real-time causal emergence intensity trajectory is obtained based on the real-time causal emergence intensity.
6. The method for quantifying the work efficiency of medical caregivers based on multidimensional data according to claim 1, characterized in that, The strategy optimization in step S5 specifically involves: The real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory constitute a three-dimensional state space. By analyzing historical performance shift data, performance regions are divided in the three-dimensional state space. Project the current status point of the medical caregiver onto the three-dimensional status space to determine the effectiveness zone; It has a built-in rule model that outputs forward-looking optimization suggestions; The output of the comprehensive performance report includes visualization charts of the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, performance area labels for key periods, and forward-looking optimization suggestions.
7. A medical care worker work efficiency quantification system based on multidimensional data, characterized in that, The system is applied to the multidimensional data-based medical care worker performance quantification method as described in any one of claims 1-6, including an information entropy field construction module, a negative entropy evaluation module, a phase space reconstruction module, a causal emergence identification module, and a strategy optimization module; The information entropy field construction module is used to acquire historical data streams, which include the historical location coordinates of medical caregivers and historical event markers. Based on the historical data streams, a ward information entropy field is constructed to obtain the location demand entropy. The negative entropy assessment module is used to continuously collect real-time data streams, which include the real-time location coordinates of medical caregivers, real-time event markers, and real-time physiological signals. Based on the real-time data streams and the location demand entropy, negative entropy assessment is performed, and the real-time negative entropy flow trajectory is output. The phase space reconstruction module is used to reconstruct the phase space based on the real-time data stream to obtain the real-time control margin trajectory. The causal emergence identification module is used to perform cross-scale causal emergence identification based on the real-time data stream and output the real-time causal emergence intensity trajectory. The strategy optimization module is used to optimize the strategy based on the real-time negative entropy flow trajectory, the real-time control margin trajectory, and the real-time causal emergence intensity trajectory, and output a comprehensive performance report.