A human-machine function allocation triggering method and device based on dynamic operation behavior

Abstract

This application discloses a method and device for triggering human-machine function allocation based on dynamic operational behavior, belonging to the field of command and control technology. It includes: collecting dynamic behavior data of the target operator; calculating a set of measurement indicators based on the dynamic behavior data; calculating a perception and decision-making capability value based on the measurement indicator set; calculating a task load index and situation urgency based on the dynamic behavior data; comparing the perception and decision-making capability value, task load index, and situation urgency with corresponding preset thresholds to trigger a human-led state, a human-machine collaborative state, or a machine-led state; and performing a next state transition based on the values ​​of the perception and decision-making capability value, task load index, and situation urgency, and the current state, according to priority. By combining the three variables of perception and decision-making capability, task load index, and situation urgency as a trigger for human-machine function allocation, it more comprehensively reflects the complex coupling relationship between "human-task-environment," improving the efficiency and safety of human-machine collaboration.

Description

Technical Field

[0001] This application belongs to the field of command and control technology, and in particular relates to a method and device for triggering human-machine function allocation based on dynamic operational behavior. Background Technology

[0002] In command and control environments, commanders need to complete situational awareness, understanding, prediction, and decision-making within a very short time. The real-time decline or fluctuation of their perception and decision-making abilities directly impacts mission success or failure. However, current personnel capability assessment and human-machine function allocation systems are largely limited by the traditional paradigm of "post-event evaluation and static division of labor." In real, highly dynamic, and highly adversarial operational environments, offline testing, post-mission debriefing, or pre-set fixed division of labor rules are insufficient to effectively address the instantaneous changes in personnel cognitive states and the real-time evolution of the mission situation.

[0003] However, existing technologies suffer from the following drawbacks: Most existing personnel capability assessment methods employ offline testing or post-task debriefing, which can only reflect overall or post-event levels and cannot continuously monitor the instantaneous changes in personnel's perceptual decision-making abilities during task execution. When personnel capabilities suddenly decline, the system cannot detect and adjust the allocation of human-machine functions in a timely manner. Some existing studies only allocate tasks based on a single dimension of task load or situational difficulty, completely ignoring the dynamic changes in personnel's own cognitive abilities. This can easily lead to situations where the machine remains silent when personnel need assistance the most, or forcibly intervenes when it is unnecessary. Conventional personnel capability assessment methods mainly focus on general indicators such as basic operation accuracy and reaction time, rarely involving characteristics that can reflect the robustness of personnel's cognition under high dynamic pressure environments, and there are no methods designed to calculate these indicators in real time based on daily operational behaviors. Multimodal assessment methods based on physiological signals are complex and costly, and are easily affected by environmental interference. Research based on operational behaviors is mostly used for offline post-event statistics, rarely for online real-time assessment, and has not formed a closed-loop linkage with dynamic human-machine function allocation mechanisms.

[0004] Current research cannot achieve real-time closed-loop adaptive adjustment of human-machine function allocation, which easily leads to problems such as delayed decision response and untimely emergency response, seriously restricting the overall effectiveness and operational safety of intelligent command and control systems. Summary of the Invention

[0005] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a human-machine function allocation triggering method and apparatus based on dynamic operational behavior, which combines three variables—comprehensive perception and decision-making capability, task load index, and situational urgency—as the trigger for human-machine function allocation. Compared with existing methods that rely solely on task volume (such as task density) or solely on external situation (such as threat level), this application comprehensively reflects the complex coupling relationship between "human-task-environment." The triggering logic is more consistent with actual command and control scenarios, effectively reducing false triggers or missed triggers caused by insufficient information in a single dimension, and improving the efficiency and safety of human-machine collaboration.

[0006] To address the aforementioned problems, according to a first aspect of this application, a method for triggering human-machine function allocation based on dynamic operational behavior is provided, the method comprising: Collect dynamic behavior data of the target operator, including timestamp, operation type, operation object, and operation result; Calculate a set of measurement indicators based on dynamic behavioral data; Calculate the perceived decision-making capability value based on the measurement index set; Calculate the task load index and situation urgency based on dynamic behavioral data; The perception and decision-making ability value, task load index and situation urgency are compared with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. Based on the values ​​of perception and decision-making capability, task load index, and situational urgency, and the current state, the next state transition is carried out according to priority.

[0007] According to one embodiment of this application, the step of calculating the perceived decision-making capability value based on a set of measurement indicators includes: Normalize each indicator in the measurement indicator set to obtain the normalized measurement indicator set; The various indicators in the normalized measurement indicator set are weighted and fused to calculate the perception and decision-making ability value. The set of measurement indicators includes the response time ratio for situational awareness under pressure, the accuracy of situational tracing, the response time ratio for situational understanding under pressure, the accuracy of threat level judgment, the response time ratio for situational anti-negative prediction, the accuracy of threat prediction, the response time ratio for situational anti-pressure decision-making, and the accuracy of decision-making.

[0008] According to one embodiment of this application, the calculation of the task load index and situation urgency based on dynamic behavioral data includes: Task density and operational behavior load index are calculated based on dynamic behavioral data. The task density and operational behavior load index are then weighted and fused according to preset weights to obtain the task load index. Obtain the remaining time pressure value from the dynamic behavior data, and obtain the situation urgency based on the remaining time pressure value, the relaxed time pressure threshold under the lowest situation, and the extreme time pressure threshold under the highest situation.

[0009] According to one embodiment of this application, the formula for calculating the operational behavior load index is as follows: in, For operation interval, For interval variance, To undo or modify the number of operations, This represents the total number of operations. This represents the maximum variance of the operating interval within the sliding window under no-load conditions. This refers to the operational load index.

[0010] According to one embodiment of this application, the formula for calculating the urgency of the situation is as follows: in, This represents the remaining time pressure value. This represents the minimum acceptable time pressure threshold. This represents the extreme time pressure threshold under the highest conditions. The urgency of the situation.

[0011] According to one embodiment of this application, comparing the perceived decision-making capability value, task load index, and situational urgency with corresponding preset thresholds to trigger a human-led state, a human-machine collaborative state, or a machine-led state includes: The perception and decision-making capability value, task load index, and situation urgency are compared with the corresponding preset thresholds. When the perception and decision-making capability value is greater than or equal to the preset capability threshold, the task load index is less than or equal to the preset load threshold, and the situation urgency is less than or equal to the preset urgency threshold, the manual control state is triggered. When only one of the following conditions is met: the perception and decision-making ability value is less than the preset ability threshold, the task load index is greater than the preset load threshold, or the situation urgency is greater than the preset urgency threshold, the human-machine collaboration state is triggered. When at least two of the following conditions are met: the perception and decision-making capability value is less than the preset capability threshold, the task load index is greater than the preset load threshold, and the situation urgency is greater than the preset urgency threshold, the machine-dominated state is triggered.

[0012] According to one embodiment of this application, the step of proceeding to the next state transition based on the values ​​of perception decision-making capability, task load index, and situational urgency, and the current state, according to priority, includes: When the current state is human-dominated, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining human-dominated state as the third priority. When the current state is a human-machine collaborative state, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-dominated state as the second priority, and maintaining human-machine collaborative state as the third priority. When the current state is machine-dominated, based on the values ​​of perception and decision-making ability, task load index, and situational urgency, the next state transition is carried out according to the following priorities: switching to human-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining machine-dominated state as the third priority.

[0013] According to a second aspect of this application, a human-machine function allocation triggering device based on dynamic operational behavior is provided, the device comprising: The data acquisition module is used to collect dynamic behavior data of the target operator, including timestamp, operation type, operation object, and operation result. The first processing module is used to calculate a set of measurement indicators based on dynamic behavioral data; The second processing module is used to calculate the perceived decision-making capability value based on the measurement index set; The third processing module is used to calculate the task load index and situation urgency based on dynamic behavioral data; The fourth processing module is used to compare the perception and decision-making capability value, task load index and situation urgency with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. The fifth processing module is used to perform the next state transition according to priority based on the values ​​of perception and decision-making capability, task load index, and situation urgency, as well as the current state.

[0014] According to a third aspect of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the human-machine function allocation triggering method based on dynamic operating behavior as described in the first aspect above.

[0015] According to a fourth aspect of this application, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the human-machine function allocation triggering method based on dynamic operation behavior as described in the first aspect above.

[0016] According to a fifth aspect of this application, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the human-machine function allocation triggering method based on dynamic operation behavior as described in the first aspect.

[0017] According to a sixth aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the human-machine function allocation triggering method based on dynamic operational behavior as described in the first aspect above.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application.

[0019] This application provides a human-computer function allocation and triggering method based on dynamic operational behavior, which has the following advantages over existing technologies: (1) This application collects dynamic behavioral data of the target operator and constructs three types of linkage trigger parameters: perception and decision-making capability value, task load index, and situation urgency. Combined with a priority state transition mechanism, it realizes the dynamic allocation of human-machine functions. It can complete the adaptive adjustment of human-machine collaborative state without additional physiological sensors, which improves the real-time performance and engineering feasibility of human-machine function allocation. Combined with the trigger rules that cover the entire scenario with three parameters, it can achieve more accurate state matching, stably adapt to different task stages and personalized scenarios of different operators, and effectively improve the scenario adaptability of the technical solution and the application value of command and control scenarios.

[0020] (2) This application constructs a multi-dimensional perception and decision-making assessment index, including the stress response time ratio and the negative response time ratio, and combines it with normalized weighted fusion to achieve accurate quantification of personnel perception and decision-making capabilities. Compared with traditional post-evaluation and single-dimensional division of labor methods, it can capture the instantaneous fluctuations of personnel's cognitive state in real time, effectively improving the problems of strong lag and inability to dynamically adjust online in traditional assessment methods, and further improving the accuracy of personnel capability assessment and the reliability of status monitoring. Based on operational behavior data, online calculation of task load and situation urgency is realized. The quantification of task and environmental status can be completed without additional hardware deployment, effectively reducing system deployment costs and environmental interference, improving the robustness of status assessment, and realizing efficient real-time tracking of personnel and task status.

[0021] (3) This application organically combines dynamic behavior data collection, multi-dimensional measurement index calculation, three-parameter linkage state triggering, and priority state conversion to form a complete closed-loop process for dynamic allocation of human-machine functions. While ensuring higher computing efficiency, it achieves more accurate adaptive adjustment of human-machine collaborative state, providing more efficient and robust technical support for human-machine collaboration and adaptive function allocation in command and control scenarios. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is one of the flowcharts illustrating the human-machine function allocation and triggering method based on dynamic operation behavior provided in this application embodiment; Figure 2 This is a diagram of the personnel perception and decision-making ability assessment index system provided in the embodiments of this application; Figure 3 This is the second flowchart of the human-machine function allocation triggering method based on dynamic operation behavior provided in the embodiments of this application; Figure 4 This is a schematic diagram of the three-variable linkage triggering state of human-machine function allocation provided in the embodiments of this application; Figure 5 This is a timing diagram of the real-time evaluation of the sliding window provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the human-machine function allocation triggering device based on dynamic operation behavior provided in the embodiments of this application; Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0024] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate to allow embodiments of this application to be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0025] The following description, in conjunction with the accompanying drawings, details the human-machine function allocation triggering method, human-machine function allocation triggering device, electronic device, and readable storage medium based on dynamic operation behavior provided in this application, through specific embodiments and application scenarios.

[0026] Among them, the human-machine function allocation triggering method based on dynamic operation behavior can be applied to the terminal, and can be executed by the hardware or software in the terminal.

[0027] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablets with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads).

[0028] The following embodiments describe a terminal including a display and a touch-sensitive surface. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0029] The human-machine function allocation triggering method based on dynamic operation behavior provided in this application embodiment can be executed by an electronic device or a functional module or functional entity in an electronic device that can implement the human-machine function allocation triggering method based on dynamic operation behavior. The electronic devices mentioned in this application embodiment include, but are not limited to, mobile phones, tablets, computers, cameras and wearable devices. The following uses an electronic device as the execution subject to describe the human-machine function allocation triggering method based on dynamic operation behavior provided in this application embodiment.

[0030] In a command and control environment, commanders need to complete situational awareness, understanding, prediction, and decision-making within a very short time. The real-time decline or fluctuation of their perception and decision-making capabilities directly affects the success or failure of the mission. Existing technologies mainly suffer from the following shortcomings: The current methods for assessing personnel capabilities primarily rely on post-event evaluations, lacking real-time dynamic adjustment capabilities. Most existing methods employ offline testing or post-task debriefing, such as evaluating operator performance after a task is completed through questionnaires, simulator playback, or expert scoring. These methods only reflect overall or post-event performance and cannot continuously monitor the instantaneous changes in personnel's perceptual and decision-making abilities during task execution. Due to the highly dynamic and uncertain nature of command and control tasks, personnel's cognitive states (such as fatigue, stress, and inattention) can fluctuate drastically within seconds, and post-event evaluations completely miss this time-sensitive information. Therefore, when personnel capabilities suddenly decline, the system cannot detect and adjust human-machine function allocation in a timely manner, easily leading to delays or errors in critical decisions. The lack of online real-time evaluation methods also prevents human-machine collaborative systems from achieving closed-loop self-adaptation, limiting the development of intelligent command and control.

[0031] The indicator system is not linked to the real-time triggering mechanism, and the human-machine allocation dimension is too simplistic: Related technologies have constructed an intelligent level assessment framework based on an observation-judgment-decision-action model. This framework focuses on classifying the capabilities of unmanned systems or AI themselves, without directly mapping the assessment results to the real-time triggering conditions for human-machine function allocation. Other studies focus on the impact of task load or situational difficulty on task allocation, such as automatically increasing or decreasing automation levels based on task density or switching human-machine interaction modes based on threat level. However, these methods allocate tasks based on only a single dimension (task or environment), completely ignoring the dynamic changes in human cognitive abilities. In actual combat, even with the same task load and situational difficulty, differences in the abilities of different operators and the cognitive fluctuations of the same operator at different times can significantly affect human-machine collaboration efficiency. Relying solely on external conditions for task allocation can easily lead to situations where "machines remain silent when personnel need help most, or forcibly intervene when unnecessary," reducing the overall effectiveness of the human-machine team.

[0032] There is a lack of online extraction methods for specific cognitive indicators such as stress resistance and resilience: Conventional personnel capability assessment methods mainly focus on general indicators such as basic operation accuracy and reaction time, rarely addressing characteristics that reflect the cognitive robustness of personnel under high dynamic pressure environments. The "stress resistance reaction time ratio" and "resilience reaction time ratio" proposed in this application are used to measure the degree to which personnel maintain their perception, understanding, prediction, and decision-making efficiency when facing time pressure (such as a sudden increase in the number of targets or a shortened decision-making time limit) and interfering information (such as false targets or irrelevant alarms). These indicators are often collected in traditional offline tests through specialized psychological experimental paradigms, which are costly, time-consuming, and cannot be integrated into the online data stream of actual operations. Existing technologies neither design methods for real-time calculation of these indicators based on daily operational behavior nor use them as trigger variables for human-machine function allocation. Therefore, in high-intensity adversarial environments, the system easily overlooks the critical point of personnel cognitive tolerance, misses the best opportunity to adjust the division of labor, and may even trigger a chain reaction of human error.

[0033] Deploying physiological sensor solutions is challenging, and operational behavior methods lack real-time linkage: While existing multimodal assessment methods based on physiological signals (EEG, ECG, eye tracking, skin conductance, etc.) can provide relatively objective indicators of cognitive load and fatigue, their equipment is complex, costly, and requires specialized personnel for wearing and maintenance. In battlefield or field exercise environments, issues such as electrode detachment, signal interference, and motion artifacts frequently occur, significantly reducing data usability. Furthermore, physiological sensors themselves may affect operator comfort and freedom of movement, and even expose equipment characteristics, posing a risk to tactical concealment. In contrast, methods based on operational behavior (such as mouse clicks, keyboard commands, and interface selection sequences) directly extract indicators from personnel-system interaction logs, offering significant advantages such as zero additional hardware, implicit data acquisition, and high environmental robustness. However, existing research based on operational behavior is mostly used for offline, post-hoc statistical analysis (such as task analysis and training evaluation), rarely for online real-time assessment, and even less so for forming a closed-loop linkage with dynamic human-machine function allocation mechanisms. This results in a large amount of valuable behavioral data being wasted, and the system is unable to proactively respond to changes in personnel status during tasks. Human-machine collaboration remains in a static or semi-static preset mode.

[0034] Figure 1 This is one of the flowcharts illustrating the human-machine function allocation and triggering method based on dynamic operation behavior provided in this application embodiment, such as... Figure 1 As shown, the human-machine function allocation triggering method based on dynamic operation behavior includes steps 110, 120, 130, 140, 150 and 160.

[0035] Step 110: Collect dynamic behavior data of the target operator, including timestamp, operation type, operation object, and operation result; As is easily understood, the system records dynamic behavioral data streams in real time. Each record includes: timestamp, operation type (such as "select target", "mark threat level", "submit decision command", etc.), operation object ID, and operation result (correct / incorrect). The system also has a built-in stress event injection module (such as suddenly increasing the number of targets or shortening the decision time limit) and interference event injection module (such as randomly popping up irrelevant information) to actively measure stress resistance / negative response.

[0036] Step 120: Calculate the measurement index set based on dynamic behavioral data; In complex and dangerous environments, personnel must balance mission requirements with human-machine collaborative mobility requirements. This application constructs an evaluation index system for commanders' perception and decision-making capabilities (Y), comprising four primary indicators: situation awareness (Y1), situation understanding (Y2), situation prediction (Y3), and situation decision-making (Y4), as well as eight secondary indicators (observational measures). Details are as follows: (1) Ability to detect situation (Y1): Two secondary indicators are set up: the reaction time ratio of the situation to stress detection (K1) and the accuracy of the source of perception (K2); or, as an optional implementation method, two secondary indicators are adopted: sensitivity to perception trend and reaction time to perception trend.

[0037] (2) Situational understanding capability (Y2): It has two sub-indicators: situational understanding stress response time ratio (K3) and threat level judgment accuracy (K4); or, as an optional implementation, threat prediction degree and threat prediction response time are adopted.

[0038] (3) Predictive situation capability (Y3): It has two sub-indicators: the time to react to the negative situation (K5) and the accuracy of threat prediction (K6).

[0039] (4) Decision-making capability (Y4): It has two sub-indicators: decision-making capability under pressure response time ratio (K7) and decision-making accuracy (K8).

[0040] Figure 2 This is a diagram of the personnel perception and decision-making ability assessment index system provided in the embodiments of this application, such as... Figure 2 As shown, a tree structure is used to display four primary indicators and their subordinate secondary indicators. The root node is "Perception and Decision-Making Ability Y", and the branches are Situation Awareness Ability Y1, Situation Understanding Ability Y2, Situation Prediction Ability Y3, and Situation Decision-Making Ability Y4.

[0041] Y1 includes core indicators: the ratio of perceived stress response time to K1 and the accuracy of perceived source tracing to K2. Optional alternative indicators are perceived trend sensitivity / perceived trend response time (represented by dashed boxes).

[0042] Y2 includes core metrics: Understanding stress response time ratio K3 and Threat level judgment accuracy K4. Optional alternative metrics are Threat prediction accuracy / Threat prediction response time.

[0043] Y3 includes prediction accuracy for negative reactions (K5) and threat prediction accuracy (K6).

[0044] Y4 includes decision stress response ratio K7 and decision accuracy K8.

[0045] Dashed arrows and dashed boxes indicate optional implementation methods.

[0046] Table 1 defines and calculates the K1-K8 indicators provided in this application embodiment. As shown in Table 1, K1 to K8 are all calculated from real-time collected dynamic operational behavior data, without relying on any physiological sensors. Among them: K1, K3, and K7 are stress resistance reaction time ratios, reflecting the cognitive response efficiency of personnel under time pressure; K5 is the negative resistance reaction time ratio, reflecting the cognitive stability of personnel in a disturbing environment; K2, K4, K6, and K8 are accuracy indicators, reflecting the correctness of situational awareness and decision-making.

[0047] Table 1 The formula for calculating the ratio of K1 to the stress response is as follows: in, The median reaction time (in seconds) of an operator from the appearance of a target to the first click / selection of that target under stress events (such as a sudden increase in the number of targets). During the offline calibration phase, the maximum perceived reaction time under pressure among all calibration personnel (i.e., the reaction time of the slowest person).

[0048] The range of values ​​for K1 is: The shorter the reaction time, the closer K1 is to 1, indicating better stress resistance; when the reaction time is close to or equal to that of the slowest person in the group, K1 approaches 0.

[0049] The formula for calculating the accuracy of K2 perception and tracing is as follows: in, The number of times an operator correctly traces the source or related information of a target. This represents the total number of source tracing tasks.

[0050] The range of values ​​for K2 is: The closer the value is to 1, the more accurate the perception and tracing. If there is no tracing task, this value is marked as Null.

[0051] The formula for calculating the ratio of stress response time in K3 is shown below: in, This represents the median time (in seconds) for an operator to respond from pushing a situational awareness segment to submitting the correct threat level during a stress event. During the calibration phase, all calibration personnel understand the maximum value of the reaction under pressure.

[0052] The range of values ​​for K3 is: The shorter the reaction time, the closer K3 is to 1, indicating a better ability to withstand pressure and comprehend.

[0053] The formula for calculating the accuracy of K4 threat level assessment is as follows: in, The threat level (e.g., level 1 to 5) submitted by the operator. The system's preset real threat level, It is the maximum possible grade difference (upper limit of grade range minus lower limit).

[0054] The range of values ​​for K4 is: The closer the value is to 1, the more accurate the threat level assessment. If no threat level is submitted, then K4=0.

[0055] The formula for calculating the ratio of K5 to predict the resistance to negative reactions is as follows: in, The median (in seconds) of the operator's reaction time to issue the next threat target prediction instruction in the event of a disruptive event (such as the appearance of a false target). This represents the maximum predicted reaction time for all calibration personnel under disturbances during the calibration phase.

[0056] The range of values ​​for K5 is: The shorter the reaction time, the closer K5 is to 1, indicating better anti-interference prediction capability.

[0057] The formula for calculating the accuracy of K6 threat prediction is as follows: in, The number of the next threat targets correctly predicted by the operator. This represents the total number of prediction opportunities.

[0058] The range of values ​​for K6 is: The closer the value is to 1, the more accurate the prediction. If there is no prediction task, it is denoted as Null.

[0059] The formula for calculating the K7 decision stress response ratio is as follows: in, This represents the median reaction time (in seconds) of an operator from the appearance of a decision prompt to the final submission of a decision instruction under stress events. This represents the maximum value of the decision-making and reaction time of all calibration personnel under pressure during the calibration phase.

[0060] The range of values ​​for K7 is: The shorter the reaction time, the closer K7 is to 1, indicating better resilience and decision-making ability.

[0061] The formula for calculating the accuracy of K8 decisions is as follows: in, Score the decision-making options submitted by the operator (automatically evaluated by the expert rule base or task logic). The score (full marks) for the optimal decision in the same decision problem.

[0062] The range of values ​​for K8 is: The closer K8 is to 1, the higher the quality of the decision. If the decision is completely wrong, K8 = 0.

[0063] In this embodiment, an active injection mechanism is designed for stress events (such as a sudden increase in the number of targets or a shortened decision-making time) and interference events (such as false targets), from which stress resistance reaction time ratios (K1, K3, K7) and negative reaction time ratios (K5) are extracted. These indicators directly measure the cognitive retention ability of personnel under time compression or information overload pressure. They require no physiological sensors and are extracted in real time from routine operational behaviors such as mouse clicks, keyboard commands, and interface selections. Yet, they can objectively and quantitatively reflect the cognitive robustness shortcomings of commanders in highly dynamic battlefield environments. The system has extremely low hardware costs, is easy and quick to deploy, and can be directly embedded into the human-machine interaction backend of existing command and control simulation training systems or actual equipment. No hardware modifications or additional sensors are required, and it does not affect the normal behavior of operators. It exhibits high battlefield environment robustness, providing a key basis for adaptive human-machine division of labor and filling the gap in existing technologies that lack real-time stress resistance indicator assessment.

[0064] Step 130: Calculate the perceived decision-making capability value based on the measurement index set; In some embodiments, calculating the perceived decision-making capability value based on a set of measurement indicators includes: Normalize each indicator in the measurement indicator set to obtain the normalized measurement indicator set; The various indicators in the normalized measurement indicator set are weighted and fused to calculate the perception and decision-making ability value. The set of measurement indicators includes the response time ratio for situational awareness under pressure, the accuracy of situational tracing, the response time ratio for situational understanding under pressure, the accuracy of threat level judgment, the response time ratio for situational anti-negative prediction, the accuracy of threat prediction, the response time ratio for situational anti-pressure decision-making, and the accuracy of decision-making.

[0065] During the offline calibration phase, at least 10 typical operators were selected to perform standard tasks in a "baseline scenario" without time pressure or interference, and their reaction times under stress / interference events were recorded. Take the maximum value of these values ​​as Once calibrated, these maximum values ​​are fixed as the normalization baseline, or they can be recalculated weekly or after every 5 tasks to adapt to changes in group capabilities.

[0066] Baseline measurement: During the low-load rehearsal phase before the mission begins (without time pressure or interference), calculate the median baseline reaction time for each operator and save it to their individual profile.

[0067] Optionally, data can be collected via a real-time sliding window: window length 60 seconds, step size 10 seconds, collecting the median reaction time under stress events within each window, and comparing it with the baseline to obtain the stress resistance / negative reaction time ratio.

[0068] It is easy to understand that, since all K values ​​fall within... The comprehensive perception and decision-making ability Y can be obtained directly by weighted summation of the intervals. Assuming that the weights of each level of indicators are equal, the eight secondary measurement indicators are comprehensively represented as the perception and decision-making ability Y of the commanders. The calculation formula is as follows: in, These are the values ​​of each indicator after min-max normalization (range [0,1]). This comprehensive capability Y is related to the task load index TL and the situational urgency level. Together, the human-machine function allocation of the intelligent collaborative unit consists of three trigger variables.

[0069] In some embodiments, to accommodate different task stages or individual differences, an objective weighted fusion method (such as the entropy weight method or the analytic hierarchy process) can be used to determine the weights of each indicator. In this case, the calculation formula for perceptual decision-making ability is as follows: Among them, the weighting coefficient satisfy The weights can be dynamically calculated by the system based on historical data. The weights can be dynamically adjusted according to the task situation; for example, the weight of stress response indicators can be increased when the urgency is high.

[0070] In this embodiment, multiple capability fusion methods are provided: the basic implementation uses an equal-weighted arithmetic average, which is simple, quick, and easy to understand, suitable for rapid prototype verification and general command scenarios; the preferred implementation introduces entropy weighting or analytic hierarchy process to dynamically determine the weights of each indicator, and can adaptively adjust according to the urgency of the situation. Through flexible weighting strategies, it can adapt to the assessment needs of different mission phases (reconnaissance, engagement, withdrawal), individual differences among personnel, and different troop levels, significantly improving the relevance, accuracy, and practicality of comprehensive capability assessment. It reduces system complexity while achieving real-time linkage.

[0071] Step 140: Calculate the task load index and situation urgency based on dynamic behavior data; In some embodiments, calculating the task load index and situation urgency based on dynamic behavioral data includes: Task density and operational behavior load index are calculated based on dynamic behavioral data. The task density and operational behavior load index are then weighted and fused according to preset weights to obtain the task load index. The task load index TL is composed of task density TF and operational behavior load index. The weighted average is obtained, and the calculation formula is shown below: in, The number of targets / instructions that need to be processed per unit time (1 minute) ÷ the system's rated maximum processing capacity. This is a load index based on operational behavior.

[0072] In some embodiments, the formula for calculating the operational load index is as follows: in, For operation interval, For interval variance, To undo or modify the number of operations, This represents the total number of operations. This represents the maximum variance of the operating interval within the sliding window under no-load conditions. This refers to the operational load index.

[0073] Obtain the remaining time pressure value from the dynamic behavior data, and obtain the situation urgency based on the remaining time pressure value, the relaxed time pressure threshold under the lowest situation, and the extreme time pressure threshold under the highest situation.

[0074] In some embodiments, the formula for calculating the urgency of the situation is as follows: in, This represents the remaining time pressure value. This represents the minimum acceptable time pressure threshold. This represents the extreme time pressure threshold under the highest conditions. The urgency of the situation.

[0075] As a simplified implementation method, It can also be 0 or 1, representing low-situation or high-situation scenarios respectively: when K1 (scenario coefficient) can only be either the low-situation scenario coefficient or the high-situation scenario coefficient, =0 or 1.

[0076] Step 150: Compare the perception and decision-making ability value, task load index and situation urgency with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. In some embodiments, comparing the perceived decision-making capability value, task load index, and situational urgency with corresponding preset thresholds to trigger a human-led state, a human-machine collaborative state, or a machine-led state includes: The perception and decision-making capability value, task load index, and situation urgency are compared with the corresponding preset thresholds. When the perception and decision-making capability value is greater than or equal to the preset capability threshold, the task load index is less than or equal to the preset load threshold, and the situation urgency is less than or equal to the preset urgency threshold, the manual control state is triggered. When only one of the following conditions is met: the perception and decision-making ability value is less than the preset ability threshold, the task load index is greater than the preset load threshold, or the situation urgency is greater than the preset urgency threshold, the human-machine collaboration state is triggered. When at least two of the following conditions are met: the perception and decision-making capability value is less than the preset capability threshold, the task load index is greater than the preset load threshold, and the situation urgency is greater than the preset urgency threshold, the machine-dominated state is triggered.

[0077] Optionally, Table 2 shows the triggering conditions and function allocation actions for different triggering states provided in the embodiments of this application.

[0078] Table 2 threshold Offline experimental calibration allows for fine-tuning based on task phases and individual operator characteristics.

[0079] Step 160: Based on the values ​​of perception and decision-making capability, task load index, and situational urgency, and the current state, proceed to the next state transition according to priority.

[0080] In some embodiments, the step of proceeding to the next state transition based on the values ​​of perception decision-making capability, task load index, and situational urgency, and the current state, according to priority, includes: When the current state is human-dominated, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining human-dominated state as the third priority. When the current state is a human-machine collaborative state, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-dominated state as the second priority, and maintaining human-machine collaborative state as the third priority. When the current state is machine-dominated, based on the values ​​of perception and decision-making ability, task load index, and situational urgency, the next state transition is carried out according to the following priorities: switching to human-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining machine-dominated state as the third priority.

[0081] Optionally, Table 3 shows the state transition conditions for different current states to the next state provided in the embodiments of this application.

[0082] Table 3 Priority order means that when multiple conditions are met simultaneously, only the highest priority transition is executed. For example, if starting from machine-led, both "directly return to human-led" and "return to human-machine collaboration" are satisfied, then returning to human-led will take priority.

[0083] In some embodiments, taking a command simulation system as an example, the method for triggering human-machine function allocation based on dynamic operational behavior is illustrated, specifically including the following steps: Step 1: System Deployment An operation behavior recording module runs in the background of the simulated command and control terminal, intercepting all human-computer interaction events (mouse clicks, keyboard commands, drop-down selections, trajectory dragging, etc.). Simultaneously, a pressure event injector and a interference injector are embedded in the system. No eye trackers, EEG caps, or heart rate monitors are installed.

[0084] Step 2: Offline calibration stage Ten typical operators were selected and performed standard tasks in a baseline scenario with no time pressure and no interference for 5 minutes. The results for each operator were recorded. Baseline reaction time , , , (take the median); Operating interval variance baseline Take the maximum value of the variance of the operator's operation interval within the sliding window when there is no load as the normalized denominator.

[0085] Thresholds were calibrated through simulation experiments: , , (Slight adjustments can be made at different stages of the task).

[0086] Step 3: Online Real-Time Assessment The system executes in a loop with a window size of 60 seconds and a step size of 10 seconds: Extract all events within the window from the operation behavior record and calculate K1~K8 (if there is no stress event, use the reaction time ratio under the most recent stress event, or set it to 1); Min-max normalization was performed on each indicator; Y(t) is calculated using equal weights (or preferred weights); Calculate TF(t) and , thus obtaining TL(t); Read the remaining time of the task and calculate. .

[0087] Step 4: Trigger human-machine function allocation Y(t), TL(t), Compare with the threshold and output instructions according to the state machine: If the system enters the "human-machine collaboration" state, it will display the decision-making assistance options on the interface in a semi-transparent manner. If the system enters "machine-dominated" mode, it will automatically execute the preset emergency plan (such as automatic evasive maneuvers) and highlight the alarm operator.

[0088] Step 5: Adaptive Update The operator's baseline reaction time is recalculated every 10 minutes (using the most recent stress-free period's operational behavior data) to achieve baseline drift adaptation.

[0089] Figure 3 This is the second flowchart illustrating the human-machine function allocation and triggering method based on dynamic operation behavior provided in this application embodiment, as follows: Figure 3 As shown, a flowchart illustrates the entire process of real-time evaluation and human-machine function allocation triggering, including the following steps: start; Real-time collection of operation behavior data (timestamp, operation type, object, result); Determine if a stress / interference event has been triggered; if so, inject it proactively. Data extraction using a sliding window (long window 60 seconds, step size 10 seconds); Calculate the eight secondary indicators K1 to K8; Perform Min-Max normalization on the metrics; Equal weighted fusion (Y=avg(K_norm)) is used, and optional objective weighted fusion is indicated by dashed boxes; Simultaneously calculate the task load index TL (based on task density TF and operational behavior load index). ) and the urgency of the situation ; Y, TL, Compare with a preset threshold; Based on the comparison results, it will enter one of three states: human-led, human-machine collaboration, or machine-led. Output and execute human-machine function allocation instructions; Determine whether the task should continue. If it should continue, return to the sliding window to retrieve the data; otherwise, end the process.

[0090] In the diagram, diamonds represent judgments, rectangles represent processing steps, and dashed lines represent optional paths.

[0091] Figure 4 This is a schematic diagram of the three-variable linkage triggering state of human-machine function allocation provided in the embodiments of this application, such as... Figure 4 As shown, a flowchart is used to illustrate the transition relationships between the three states.

[0092] Human-led mode: Human decision-making, machine only provides prompts.

[0093] Human-machine collaboration status: The machine provides assistance suggestions, and the personnel confirm and execute them.

[0094] Machine-controlled mode: The machine automatically performs emergency actions and simultaneously alerts personnel.

[0095] State transition conditions: General principles Priority order: For each state, the most urgent condition (machine-led) is checked first, followed by the mitigation conditions (human-led or human-machine collaboration), and finally the current state is maintained.

[0096] The transformation conditions are all based on three real-time variables: Personnel's comprehensive perception and decision-making ability Task load index urgency of the situation Threshold: Calibration was performed through offline experiments.

[0097] 1) The specific transitions from artificially controlled to other states are shown in Table 4. Table 4 2) The specific transitions between human-machine collaboration and other states are shown in Table 5. Table 5 3) The specific transitions from machine-dominated to other states are shown in Table 6. Table 6 Figure 5 This is a timing diagram of the real-time evaluation of the sliding window provided in the embodiments of this application, such as... Figure 5 As shown, a Gantt chart is used, with the horizontal axis representing time (seconds), to show the sliding method of the long window (60 seconds, step size 10 seconds) and the calculation trigger point.

[0098] The long window slides sequentially from 0-60 seconds, 10-70 seconds, 20-80 seconds, and so on.

[0099] At the end of each window (60 seconds, 70 seconds, 80 seconds...), the trigger point "Calculate Y, TL, dSAU" is marked with a red diamond.

[0100] The figure exemplarily illustrates the pressure event injection (15 seconds, lasting 5 seconds) and the disturbance event injection (45 seconds, lasting 3 seconds) used to actively measure the stress resistance / negative response time ratio.

[0101] The vertical axis is divided into three areas: "long window", "calculation trigger point" and "stress / interference event", which clearly express the overlapping relationship in time.

[0102] The human-machine function allocation and triggering method based on dynamic operation behavior provided in this application can be executed by a human-machine function allocation and triggering device based on dynamic operation behavior. This application uses the execution of the human-machine function allocation and triggering method based on dynamic operation behavior by a human-machine function allocation and triggering device based on dynamic operation behavior as an example to illustrate the human-machine function allocation and triggering device based on dynamic operation behavior provided in this application.

[0103] In this embodiment, by employing a dual sliding window mechanism (a long window for stability estimation and a short window for anomaly detection), it is possible to update personnel's perceived decision-making ability, task load index, and situational urgency on a second-by-second basis. Compared to traditional post-event evaluations or fixed-period offline tests, this approach can continuously track fluctuations in cognitive state during task execution, promptly detect capability decline or overload trends, thereby supporting dynamic adjustments to human-machine function allocation and significantly improving the system's real-time adaptability.

[0104] This application also provides a human-machine function allocation triggering device based on dynamic operation behavior, such as... Figure 6 As shown, the human-machine function allocation triggering device based on dynamic operation behavior includes: a data acquisition module 610, a first processing module 620, a second processing module 630, a third processing module 640, a fourth processing module 650, and a fifth processing module 660.

[0105] The data acquisition module 610 is used to collect dynamic behavior data of the target operator, including timestamp, operation type, operation object and operation result; The first processing module 620 is used to calculate a set of measurement indicators based on dynamic behavioral data; The second processing module 630 is used to calculate the perceived decision-making capability value based on the measurement index set; The third processing module 640 is used to calculate the task load index and situation urgency based on dynamic behavior data; The fourth processing module 650 is used to compare the perception decision-making ability value, task load index and situation urgency with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. The fifth processing module 660 is used to perform the next state transition according to priority based on the values ​​of perception and decision-making capability, task load index, situation urgency and current state.

[0106] The human-machine function allocation triggering method based on dynamic operational behavior provided in this application combines three variables—comprehensive perception and decision-making ability, task load index, and situational urgency—as the trigger for human-machine function allocation. Compared with existing methods that rely solely on task volume (such as task density) or external situation (such as threat level), this method more comprehensively reflects the complex coupling relationship between "human-task-environment." The triggering logic is more consistent with actual command and control scenarios, effectively reducing false triggers or missed triggers caused by insufficient information in a single dimension, and improving the efficiency and safety of human-machine collaboration.

[0107] The human-machine function allocation triggering device based on dynamic operation behavior provided in this application embodiment can achieve... Figures 1 to 2 The various processes implemented in the embodiment of the human-machine function allocation triggering method based on dynamic operation behavior will not be described in detail here to avoid repetition.

[0108] In some embodiments, such as Figure 7 As shown, this application embodiment also provides an electronic device 700, including a processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701. When the program is executed by the processor 701, it implements the various processes of the above-described human-machine function allocation triggering method embodiment based on dynamic operation behavior and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0109] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0110] This application also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described human-machine function allocation triggering method embodiment based on dynamic operation behavior and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0111] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0112] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described human-machine function allocation triggering method based on dynamic operation behavior.

[0113] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0114] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described human-machine function allocation triggering method based on dynamic operation behavior, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0115] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a device-level chip, device chip, chip device, or on-chip device chip, etc.

[0116] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the human-machine function allocation triggering method based on dynamic operation behavior of the various embodiments of this application.

[0118] In the description of this application, "first feature" and "second feature" may include one or more of the features.

[0119] In the description of this application, "multiple" means two or more.

[0120] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0121] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0122] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for triggering human-computer function allocation based on dynamic operation behavior, characterized in that, The method includes: Collect dynamic behavior data of the target operator, including timestamp, operation type, operation object, and operation result; Calculate a set of measurement indicators based on dynamic behavioral data; Calculate the perceived decision-making capability value based on the measurement index set; Calculate the task load index and situation urgency based on dynamic behavioral data; The perception and decision-making ability value, task load index and situation urgency are compared with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. Based on the values ​​of perception and decision-making capability, task load index, and situational urgency, and the current state, the next state transition is carried out according to priority.

2. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 1, characterized in that, The calculation of the perception decision-making capability value based on the measurement index set includes: Normalize each indicator in the measurement indicator set to obtain the normalized measurement indicator set; The various indicators in the normalized measurement indicator set are weighted and fused to calculate the perception and decision-making ability value. The set of measurement indicators includes the response time ratio for situational awareness under pressure, the accuracy of situational tracing, the response time ratio for situational understanding under pressure, the accuracy of threat level judgment, the response time ratio for situational anti-negative prediction, the accuracy of threat prediction, the response time ratio for situational anti-pressure decision-making, and the accuracy of decision-making.

3. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 1, characterized in that, The calculation of task load index and situation urgency based on dynamic behavioral data includes: Task density and operational behavior load index are calculated based on dynamic behavioral data. The task density and operational behavior load index are then weighted and fused according to preset weights to obtain the task load index. Obtain the remaining time pressure value from the dynamic behavior data, and obtain the situation urgency based on the remaining time pressure value, the relaxed time pressure threshold under the lowest situation, and the extreme time pressure threshold under the highest situation.

4. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 3, characterized in that, The formula for calculating the operational load index is as follows: in, For operation interval, For interval variance, To undo or modify the number of operations, This represents the total number of operations. This represents the maximum variance of the operating interval within the sliding window under no-load conditions. This refers to the operational load index.

5. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 3, characterized in that, The formula for calculating the urgency of the situation is as follows: in, This represents the remaining time pressure value. This represents the minimum acceptable time pressure threshold. This represents the extreme time pressure threshold under the highest conditions. The urgency of the situation.

6. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 3, characterized in that, The step of comparing the perceived decision-making capability value, task load index, and situational urgency with corresponding preset thresholds to trigger a human-led state, a human-machine collaborative state, or a machine-led state includes: The perception and decision-making capability value, task load index, and situation urgency are compared with the corresponding preset thresholds. When the perception and decision-making capability value is greater than or equal to the preset capability threshold, the task load index is less than or equal to the preset load threshold, and the situation urgency is less than or equal to the preset urgency threshold, the manual control state is triggered. When only one of the following conditions is met: the perception and decision-making ability value is less than the preset ability threshold, the task load index is greater than the preset load threshold, or the situation urgency is greater than the preset urgency threshold, the human-machine collaboration state is triggered. When at least two of the following conditions are met: the perception and decision-making capability value is less than the preset capability threshold, the task load index is greater than the preset load threshold, and the situation urgency is greater than the preset urgency threshold, the machine-dominated state is triggered.

7. The human-machine function allocation and triggering method based on dynamic operation behavior according to claim 6, characterized in that, Based on the values ​​of perception and decision-making capability, task load index, and situational urgency, and the current state, the next state transition is performed according to priority, including: When the current state is human-dominated, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining human-dominated state as the third priority. When the current state is a human-machine collaborative state, based on the values ​​of perception and decision-making ability, task load index and situation urgency, the next state transition is carried out according to the following priorities: switching to machine-dominated state as the first priority, switching to human-dominated state as the second priority, and maintaining human-machine collaborative state as the third priority. When the current state is machine-dominated, based on the values ​​of perception and decision-making ability, task load index, and situational urgency, the next state transition is carried out according to the following priorities: switching to human-dominated state as the first priority, switching to human-machine collaborative state as the second priority, and maintaining machine-dominated state as the third priority.

8. A human-machine function allocation triggering device based on dynamic operation behavior, implemented using the human-machine function allocation triggering method based on dynamic operation behavior as described in any one of claims 1 to 7, characterized in that, The device includes: The data acquisition module is used to collect dynamic behavior data of the target operator, including timestamp, operation type, operation object, and operation result. The first processing module is used to calculate a set of measurement indicators based on dynamic behavioral data; The second processing module is used to calculate the perceived decision-making capability value based on the measurement index set; The third processing module is used to calculate the task load index and situation urgency based on dynamic behavioral data; The fourth processing module is used to compare the perception and decision-making capability value, task load index and situation urgency with the corresponding preset thresholds to trigger the human-led state, human-machine collaborative state or machine-led state. The fifth processing module is used to perform the next state transition according to priority based on the values ​​of perception and decision-making capability, task load index, and situation urgency, as well as the current state.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the human-machine function allocation triggering method based on dynamic operation behavior as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the human-machine function allocation triggering method based on dynamic operation behavior as described in any one of claims 1 to 7.

Images