A method and system for alerting of training fatigue accumulation

Abstract

The application discloses a kind of training fatigue accumulation warning method and system, it is related to digital training warning technical field, it is difficult to identify the safety risk of fatigue accumulation of student in the process of training Problem.The application embodiment is in the case where the time consumed by student training exceeds time consumption baseline, based on the deviation between timeout amplitude, physiological data and physiological baseline, and the fatigue conduction coefficient between training nodes Calculate cumulative fatigue index, the risk brought by the fatigue accumulated by student can be measured;Then calculate training error to measure the conversion tendency of the risk, and issue a call signal based on the conversion tendency to alarm.Using the application embodiment, the safety risk of fatigue accumulation of student in the training process can be accurately identified, and timely alarm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital training warning, and in particular to a training fatigue accumulation warning method and system. BACKGROUND

[0002] In high-intensity training scenarios such as fire drills and special operations, digital training systems, as the core technical means to ensure training safety and effectiveness, have been widely used in physiological state monitoring, training process management and other aspects.

[0003] Currently, digital training systems usually collect instantaneous physiological data of trainees in real time through wearable sensors, including heart rate, blood pressure, blood oxygen saturation, electromyographic signals, etc., and trigger alarms based on preset thresholds to determine the immediate physical state of trainees.

[0004] In structured training scenarios, training tasks are divided into multiple progressive nodes. When a trainee exceeds the time limit to complete a task due to excessive physical consumption, the trainee's body is already in an overloading state, and the training fatigue of subsequent nodes will accelerate accumulation, which may eventually lead to sudden exhaustion, muscle strains, and even cardiovascular accidents. The current system only relies on instantaneous physiological indicators to determine safety risks, ignoring the correlation between training process node delays and fatigue accumulation, which may lead to ineffective prediction of safety risks.

[0005] Therefore, there is a need for a training fatigue accumulation warning method and system. SUMMARY

[0006] To solve the problem that the prior art is difficult to identify the safety risk of trainee fatigue accumulation during training, the present application provides a training fatigue accumulation warning method and system, which can accurately identify the safety risk of trainee fatigue accumulation during training. The specific technical solutions are as follows:

[0007] In a first aspect, the present application provides a training fatigue accumulation warning method, comprising:

[0008] The real-time time consumption and real-time physiological data of the trainee at the first training node are obtained, and a personal baseline including a physiological baseline and a time consumption baseline is obtained, the physiological baseline being calculated based on historical physiological data of the trainee when training at the first training node, and the time consumption baseline being calculated based on historical time consumption average of the trainee completing the first training node; in a case where a difference between the real-time time consumption and the time consumption baseline is greater than a preset first threshold, a cumulative fatigue index of the trainee at the first training node is calculated based on a deviation value, a fatigue transmission coefficient, and a node overtime amplitude, wherein the deviation value is used to indicate a deviation between the real-time physiological data and the physiological baseline, the node overtime amplitude is calculated based on a difference between the real-time time consumption and the time consumption baseline, and the time consumption baseline, and the fatigue transmission coefficient is used to indicate a fatigue influence weight of a previous node on a subsequent node in a training process; in a case where the trainee enters a second training node, the second training node being a subsequent node of the first training node, an ability attenuation index of the trainee is calculated based on the cumulative fatigue index of the trainee at the first training node; in a case where the ability attenuation index is greater than a preset second threshold, a first call signal is sent to a trainee terminal of the trainee, the first call signal being used to prompt the trainee to be in a fatigue state and instruct the trainee to feed back the first call signal; in a case where the trainee does not feed back and a training error at the second training node is greater than the ability attenuation index, a second call signal is sent to the trainee terminal, and a third call signal and alarm information are sent to a trainer terminal, wherein the second call signal is used to instruct the trainee to pause training, the third call signal is used to instruct a trainer to assist the trainee, and the alarm information includes a traceability path report of the cumulative fatigue index of the trainee.

[0009] The training error refers to a deviation percentage of real-time training data of the trainee at the training node and a historical training data average.

[0010] The management platform can calculate the real-time training data of the trainee at the second training node through feedback of the training device or recognition of the training video stream collected by the photography device, calculate a historical training data average of the trainee at the second training node, then calculate an absolute value of a difference between the real-time training data and the historical training data average, and divide the absolute value of the difference by the historical training data average to obtain a deviation percentage as the training error.

[0011] Preferably, in a case where the trainee does not feed back and the training error at the second training node is greater than the ability attenuation index, the method further includes: issuing a power-off instruction to the training device of the trainee, the power-off instruction being used to instruct the training device to turn off a power supply of the training device itself; and the third call signal is further used to instruct the trainer terminal to drive a vibration motor of the trainer terminal to continuously vibrate until the trainer feeds back the third call signal.

[0012] Preferably, before the step of calculating the cumulative fatigue index of the trainee at the first training node based on the deviation value, the fatigue conduction coefficient and the node overtime amplitude, the method further comprises: obtaining a physical level factor of the trainee, a preset decay coefficient and a node type correction coefficient; and calculating the fatigue conduction coefficient based on the node type correction coefficient between the first training node and the second training node, the physical level factor and the decay coefficient.

[0013] Preferably, the step of calculating the cumulative fatigue index of the trainee at the first training node based on the deviation value, the fatigue conduction coefficient and the node overtime amplitude comprises: obtaining a cumulative fatigue index of the trainee at a third training node, the third training node being a previous node of the first training node; calculating a conduction fatigue based on the cumulative fatigue index of the trainee at the third training node and the fatigue conduction coefficient; calculating a current fatigue based on the deviation value and the node overtime amplitude; and calculating the cumulative fatigue index of the trainee at the first training node based on the conduction fatigue and the current fatigue.

[0014] Preferably, the deviation value comprises a first deviation value and a second deviation value; and after the step of calculating the cumulative fatigue index of the trainee based on the deviation value, the fatigue conduction coefficient and the node overtime amplitude, the method further comprises: obtaining the first deviation value after the trainee completes the first training node, and the second deviation value after the trainee completes the third training node; and updating the fatigue conduction coefficient based on the first deviation value and the second deviation value.

[0015] Preferably, the step of calculating the ability decay index of the trainee based on the cumulative fatigue index comprises: obtaining a recovery ability coefficient of the trainee, an environment correction coefficient and a basic decay coefficient of the second training node; calculating a real-time decay coefficient based on the recovery ability coefficient, the environment correction coefficient and the basic decay coefficient; and calculating the ability decay index based on the cumulative fatigue index and the real-time decay coefficient.

[0016] Preferably, after the trainee completes the first training node, the method further comprises: obtaining an average time consumption of the trainee in the last N times of completing the first training node, N being less than a total number of times of the trainee completing the first training node; and updating the time consumption baseline based on the average time consumption.

[0017] In a second aspect, an embodiment of the present application provides a training fatigue accumulation warning system, applied to the method of the first aspect, the system comprising a management platform, a trainer terminal and a trainee terminal.

[0018] The management platform is configured to acquire real-time time consumption of the trainee at the first training node, real-time physiological data of the trainee at the first training node, and a personal baseline of the trainee, the personal baseline including a physiological baseline and a time consumption baseline, the physiological baseline being calculated based on historical physiological data of the trainee when training at the first training node, and the time consumption baseline being calculated based on a historical average time consumption of the trainee for completing the first training node;

[0019] In a case where a difference between the real-time time consumption and the time consumption baseline is greater than a preset first threshold, the management platform is further configured to calculate a cumulative fatigue index of the trainee at the first training node based on a deviation value, a fatigue transmission coefficient, and a node timeout amplitude, wherein the deviation value is used to indicate a deviation between the real-time physiological data and the physiological baseline, the node timeout amplitude is calculated based on a difference between the real-time time consumption and the time consumption baseline and the time consumption baseline, and the fatigue transmission coefficient is used to indicate a fatigue influence weight of a previous node on a subsequent node in a training process;

[0020] In a case where the trainee enters a second training node, the management platform is further configured to calculate an ability attenuation index of the trainee based on the cumulative fatigue index of the trainee at the first training node, wherein the second training node is a subsequent node of the first training node;

[0021] In a case where the ability attenuation index is greater than a preset second threshold, the management platform is further configured to send a first call signal to a trainee terminal of the trainee, the first call signal being used to prompt the trainee to be in a fatigue state and instruct the trainee to feed back to the first call signal;

[0022] In a case where the trainee does not feed back and a training error at the second training node is greater than the ability attenuation index, the management platform is further configured to send a second call signal to the trainee terminal and send a third call signal and alarm information to a trainer terminal, wherein the second call signal is used to instruct the trainee to pause training, the third call signal is used to instruct a trainer to assist the trainee, and the alarm information includes a traceability path report of the cumulative fatigue index of the trainee.

[0023] In a third aspect, an embodiment of the present application provides a computing device, including a memory configured to store a program, and a processor configured to load the program to execute the method in the first aspect.

[0024] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including a stored program, wherein the program controls a device where the computer-readable storage medium is located to execute the method in the first aspect when the program runs.

[0025] Compared with the prior art, the beneficial effects of the present application are that, in the case that the time consumed by the trainee training exceeds the time consumed baseline, the cumulative fatigue index is calculated based on the deviation between the overtime amplitude, the physiological data and the physiological baseline, and the fatigue conduction coefficient between the training nodes, the risk caused by the current cumulative fatigue of the trainee can be measured, then the conversion tendency of the risk is measured by calculating the training error, and a call signal is sent based on the conversion tendency to give an alarm. By adopting the embodiment of the present application, the safety risk of fatigue accumulation of the trainee in the training process can be accurately identified, and timely alarm can be given. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the specific embodiments or the prior art description will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual proportion.

[0027] Figure 1 A system architecture diagram of a training fatigue accumulation alarm system provided by the embodiment of the present application;

[0028] Figure 2 A flowchart of a training fatigue accumulation alarm method provided by the embodiment of the present application;

[0029] Figure 3 A structural schematic diagram of a computing device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0031] It should be understood that, when used in the specification and the appended claims, the terms "comprise" and "include" indicate the existence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0032] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0033] It should be further understood that the term "and / or" used in the description and claims of the application means one or more of the associated listed items as well as all possible combinations of the items and includes these combinations.

[0034] The work of the function personnel of the public sector such as fire fighting is related to social safety and people's life and property safety, so the daily training of the emergency disposal ability, physical quality and professional skill of the function personnel is an essential link. In the present, with the population growth, urban development and material abundance, the function personnel face more and more complex situations and scenes, so the training requirements are also increasing.

[0035] It can be understood that in the present application document, the training personnel are collectively referred to as trainees, and the on-site personnel who provide guidance and management during the training are referred to as coaches.

[0036] The traditional method adopts wearable sensors to collect the instantaneous physiological data of the trainees in real time, combines the preset threshold to trigger the alarm mode to judge the instantaneous physical state of the trainees, so as to identify the safety risk of the trainees. This way ignores the correlation between the training process node delay and fatigue accumulation, and it is difficult to identify the safety risk caused by fatigue accumulation of the trainees. In order to solve this problem, the present application embodiment provides a training fatigue accumulation alarm method and system, which can accurately identify the safety risk of fatigue accumulation of the trainees during the training and timely alarm.

[0037] In order to better understand the present application embodiment, the system architecture used in the present application embodiment will be described first.

[0038] Please refer to Figure 1 , Figure 1 The system architecture diagram of a training fatigue accumulation alarm system provided by the present application embodiment is shown in Figure 1 , which includes a management platform 10, a photography device 20, a training device 30, a coach terminal 40 and a trainee terminal 50; wherein the management platform 10 can communicate with other devices in the system through wired network or wireless network respectively.

[0039] Among them, the management platform 10 is used to manage the photography device 20, the training device 30, the coach terminal 40 and the trainee terminal 50, such as the addition and deletion of the devices; it is also used to manage the project establishment of the training, the process adjustment, the qualified requirements of the training nodes, the real-time monitoring of the training process and the safety risk alarm, which is the operation core of the alarm system.

[0040] The management platform 10 can be deployed on a server, specifically, a blade server, a high-density server, a rack server, a cabinet server, a general-purpose server, a graphics processing unit (GPU) server, a data processing unit (DPU) server, or an artificial intelligence (AI) server, etc. The management platform 10 can also be lightweightly run on a terminal, such as a personal computer, a notebook computer, a smart phone, a tablet computer, an Internet of Things device, and a portable wearable device, which can be a smart watch, a smart bracelet, etc. The embodiments of the present application do not specifically limit the specific form of the device deployed by the management platform 10.

[0041] The photography device 20 is configured to acquire a real-time video stream of the trainee during the training, and transmit the real-time video stream to the management platform 10, so that the management platform 10 can perform real-time monitoring and security risk warning based on the real-time video stream. For example, the photography device 20 is a camera. In some insufficient training scenarios, the trainee or the trainer can use a mobile phone to communicate with the management platform 10 as the photography device 20 to take pictures.

[0042] The training device 30 is configured to provide conditions for the training of the trainee, such as a gun simulation device, a laser confrontation device, and an electronic shooting range device, etc.

[0043] The trainer terminal 40 is configured to receive the call signal and the alarm information sent by the management platform 10, and perform tactile vibration based on the call signal, and play a voice prompt related to the risk of the trainee, so that the trainer can quickly locate the trainee with a security risk and locate the risk reason.

[0044] The trainer terminal 40 is a terminal that the trainer can carry during the training, specifically, a notebook computer, a smart phone, a tablet computer, an Internet of Things device, and a portable wearable device, which can be a smart watch, a smart bracelet, and a head-mounted device, etc. The head-mounted device can be smart glasses that do not affect real vision.

[0045] The trainee terminal 50 is configured to receive the call signal sent by the management platform 10, and perform tactile vibration based on the call signal, and trigger a buzzer or a voice to play a voice prompt related to fatigue accumulation, and is further configured to acquire physiological parameters of the trainee during the training, and perform alarm based on the real-time physiological parameters and a preset threshold.

[0046] The trainee terminal 50 is a terminal that the trainee can carry during the training process, which can be a smart phone or a portable wearable device, such as a smart watch, a smart bracelet, and a head-mounted device. The head-mounted device can be smart glasses that do not affect the trainee's training.

[0047] It should be noted that in specific implementation, the system architecture can be any architecture including Figure 1 similar structures. The embodiments of the present application do not limit the specific composition of the system architecture. In addition, Figure 1 the composition of the architecture shown in the foregoing does not constitute a limitation on the system architecture, and in addition to the devices shown in Figure 1 , the system architecture can include more or fewer devices than shown.

[0048] Based on the above system architecture, please refer to Figure 2 , Figure 2 a flowchart of a training fatigue accumulation warning method provided by an embodiment of the present application, which is applied to the training fatigue accumulation warning system described above; as shown in Figure 2 , the method comprises the following steps:

[0049] Step 201: The management platform obtains the real-time time consumption, real-time physiological data, and personal baseline of the trainee at the first training node.

[0050] The first training node is any training node in the training process. When the trainee is at the first training node for training, the management platform can obtain the time when the trainee starts to perform the action or task of the first training node through the trainee terminal and calculate the real-time time consumption, and obtain the real-time physiological data of the trainee collected by the trainee terminal in real time, and perform aggregation and monitoring and calculation.

[0051] The personal baseline includes a physiological baseline and a time consumption baseline. The physiological baseline is calculated based on the historical physiological data of the trainee when training at the first training node, and the time consumption baseline is calculated based on the historical time consumption average of the trainee completing the first training node. Specifically, the personal baseline is stored in the archive data of the trainee in the management platform, and the management platform can directly obtain it from the database.

[0052] For example, the management platform can record the start time of the trainee at each node and the completion time of the mentioned task to obtain the time consumption of completing each node. Then, the average is calculated based on the historical time consumption to obtain the time consumption baseline.

[0053] For example, the physiological data includes blood oxygen saturation (hereinafter referred to as blood oxygen) and heart rate.

[0054] Exemplarily, the management platform can use a relational database to store the node completion records of each trainee, and the structured fields include trainee ID, node ID, completion time consumption, average heart rate, average blood oxygen, and update timestamp.

[0055] Preferably, the management platform obtains the historical time consumption of the trainee in completing the first training node, and removes the time consumption samples whose difference with the historical average is greater than the standard deviation of the historical time consumption; then calculates the average of the remaining time consumption samples to obtain the time consumption baseline.

[0056] Preferably, the management platform can obtain the historical average of various physiological data of the trainee during the training of the first training node as the physiological baseline corresponding to these physiological data.

[0057] In other possible implementations, the calculation formula of the physiological baseline includes wherein is the physiological baseline value, is the historical average heart rate of the trainee during the training of the first training node, is the historical average blood oxygen, is the weight coefficient.

[0058] It can be understood that when the trainee has a disease history that will cause greater fluctuations in a specific type of physiological data, the management platform can adjust the weight coefficient accordingly. If the trainee has a cardiovascular disease history, the weight coefficient of blood oxygen will be increased.

[0059] Preferably, after the trainee completes the first training node, the management platform further obtains the average time consumption of the trainee in completing the first training node for the last N times, N being less than the total number of times the trainee completes the first training node; then updates the time consumption baseline based on the average time consumption.

[0060] wherein the expression for updating the time consumption baseline includes:

[0061] ;

[0062] wherein , are the updated and the updated time consumption baseline values respectively, is the new data weight ratio, is the average of the last N times of completing the first training node.

[0063] Exemplarily, N is 3, is 0.2. It can be understood that can be dynamically adjusted based on the training time of the trainee. The trainee who has been trained for a long time is lower, and the trainee who is new to training is higher.

[0064] Step 202, in the case that the difference between the real-time time consumption and the time consumption baseline is greater than a preset first threshold, the management platform calculates the cumulative fatigue index of the trainee at the first training node based on a deviation value, a fatigue conduction coefficient and a node timeout amplitude.

[0065] In the training scenario, the trainee has a high level of engagement, and the difference between the real-time time consumption and the time consumption baseline can indicate the degree of fatigue of the trainee relative to the normal training state. When this difference is greater than a certain degree, it can be judged that the trainee is in a more fatigued state, and the current cumulative fatigue index of the trainee needs to be calculated to assess the trainee and the safety risk.

[0066] The management platform can obtain the fatigue perception and objective physiological indicators (such as electroencephalogram signals) of the trainee under different timeout amplitudes from historical training data or experimental data, and then select the timeout amplitude corresponding to the minimum sum of the fatigue false alarm rate and the fatigue miss rate as the first threshold. In this way, the recognition accuracy of the fatigue state of the trainee can be improved, and the fatigue false alarm rate and the fatigue miss rate can be reduced.

[0067] It can be understood that the fatigue false alarm rate refers to the probability that a trainee who is not in a fatigue state is incorrectly determined to be in a fatigue state, and the fatigue miss rate refers to the probability that a trainee who is already in a fatigue state is not identified.

[0068] For example, in the case that the difference between the real-time time consumption and the time consumption baseline is greater than the first threshold, the trainee terminal of the trainee can increase the sampling frequency from 1 Hz to 2 Hz.

[0069] For example, the first threshold is 20% of the time consumption baseline value.

[0070] The deviation value is used to indicate the deviation between the real-time physiological data and the physiological baseline, and the node timeout amplitude is calculated based on the difference between the real-time time consumption and the time consumption baseline and the time consumption baseline.

[0071] Specifically, the management platform can obtain the node timeout amplitude by dividing the difference between the real-time time consumption and the time consumption baseline by the time consumption baseline value.

[0072] Preferably, the calculation formula of the deviation value comprises:

[0073] ;

[0074] wherein, are the real-time heart rate and blood oxygen saturation, respectively, △P is the deviation value, is a weight coefficient.

[0075] Specifically, if the first training node is an endurance training node, the weight coefficient of the increased heart rate is ; if the first training node is a high-intensity training node, the weight coefficient of the blood oxygen saturation can be 0.9, and the weight coefficient of the blood oxygen saturation can be 0.1 .

[0076] For example, the first training node is a weight cross-country, may be 0.9 and 0.1 respectively; the first training node is a diving closed gas, may be 0.3 and 0.7 respectively; the first training node is a tactical shooting, may be 0.6 and 0.4 respectively.

[0077] Preferably, the management platform can sample in a 5-second sliding time window, and calculate the deviation value based on the data in the sliding time window. Special cases can be avoided to cause instantaneous interference, such as poor contact of sensor devices and other abnormalities.

[0078] The fatigue transmission coefficient is used to indicate the fatigue influence weight of the previous node on the next node in the training process. Specifically, the fatigue transmission coefficient can be preset in the database of the management platform after being rated by experts or experimentally calibrated, or can be calculated in real time by the management platform.

[0079] Preferably, the management platform can first obtain the physical level factor of the trainee, the preset attenuation coefficient and the node type correction coefficient; then based on the node type correction coefficient between the first training node and the second training node, the physical level factor and the attenuation coefficient, the fatigue transmission coefficient is calculated.

[0080] The second training node is the next node of the first training node.

[0081] The management platform can analyze the training process in the training project book, split the process into a discrete node sequence, and then represent the sequential dependency relationship between the nodes in the form of a directed graph; then based on the node types of the previous and next nodes in the sequential dependency relationship, the edge weight of the edge between the corresponding nodes is given as the node type correction coefficient.

[0082] Specifically, the value of the node type correction coefficient is set based on expert experience.

[0083] Specifically, if the previous and next nodes are a high-intensity training node and a high-precision training node respectively, the trainee's physical effort will significantly reduce shooting stability, so the node type correction coefficient is high, such as 1.8; if the previous and next nodes are both low-intensity training nodes, the fatigue transmission is weak, so the node type correction coefficient is low, such as 0.9; if the previous and next nodes are a training node with high mental load and a training node with high physical load respectively, the trainee's mental fatigue aggravates physical consumption, so the node type correction coefficient is high, such as 1.6.

[0084] Specifically, the calculation formula of the fatigue conduction coefficient comprises:

[0085]

[0086] wherein, is a fatigue conduction coefficient between a first training node i and a second training node j, is a physical fitness level factor, is a node type correction coefficient.

[0087] Specifically, the physical fitness level factor is determined by the physical fitness level of the trainee, and the two are inversely proportional. The trainee with high physical fitness level has small physical fitness level factor and small fatigue conduction coefficient; otherwise, the fatigue conduction coefficient is large.

[0088] Preferably, the deviation value comprises a first deviation value and a second deviation value; the management platform can obtain the first deviation value after the trainee completes the first training node, and the second deviation value after the trainee completes a third training node; based on the first deviation value and the second deviation value, the fatigue conduction coefficient is updated.

[0089] Wherein, the third training node is a node before the first training node.

[0090] Wherein, the fatigue conduction coefficient can correspond directly to the trainee, and the management platform can use the actual physiological data change of the trainee to feed back and correct the fatigue conduction coefficient.

[0091] Specifically, the calculation formula for updating the fatigue conduction coefficient comprises:

[0092]

[0093] wherein, , are fatigue conduction coefficients before and after updating respectively, is a first deviation value, is a second deviation value.

[0094] Preferably, the management platform can obtain the cumulative fatigue index of the trainee at the third training node; based on the cumulative fatigue index at the third training node and the fatigue conduction coefficient, the conduction fatigue is calculated; based on the deviation value and the node timeout range, the current fatigue is calculated; based on the conduction fatigue and the current fatigue, the cumulative fatigue index of the trainee at the first training node is calculated.

[0095] Wherein, the cumulative fatigue index can be expressed as the sum of the conduction fatigue and the current fatigue, that is, the sum of the fatigue accumulated at the preceding node and the fatigue generated at the current node.

[0096] Wherein, the calculation formula of the cumulative fatigue index can comprise:

[0097] ​​ ;

[0098] wherein, is the accumulated fatigue index of the previous node, is the current deviation value, is the fatigue conduction coefficient of the previous node i to the current node j; K is the overtime fatigue gain index, is the node overtime amplitude, which is used to quantify the fatigue acceleration accumulation caused by time pressure. If the previous node is the first node, is 0.

[0099] The conduction fatigue of the calculation formula of the accumulated fatigue index can avoid cross-node fatigue linear accumulation distortion.

[0100] The current fatigue of the calculation formula of the accumulated fatigue index can capture the fatigue acceleration phenomenon caused by time pressure.

[0101] For example, when the first training node is a physical training node, K takes a value of 0.5; when the first training node is a precision operation node, K takes a value of 0.4; when the first training node is a theoretical learning node, K takes a value of 0.2.

[0102] Wherein, the management platform can obtain the training data of the trainee in the third training node, and then based on the training data, calculate the accumulated fatigue index of the trainee in the third training node according to the above calculation formula of the accumulated fatigue index. If the third training node is the first node of the trainee's training process, the third training node has no corresponding previous node, so the conduction fatigue in the calculation formula is 0; if the third training node is not the first node, the management platform needs to obtain the accumulated fatigue index of the previous node of the third training node to calculate the conduction fatigue; the process of the management platform obtaining the accumulated fatigue index of the "previous node" is similar to the process of obtaining the accumulated fatigue index of the third training node described in this paragraph, and so on.

[0103] Step 203, in the case that the trainee enters the second training node, the management platform calculates the ability attenuation index of the trainee based on the accumulated fatigue index in the first training node.

[0104] Wherein, when the trainee enters a new node, the management platform can calculate the ability attenuation index of the trainee according to the basic attenuation coefficient of the new node affected by fatigue to predict the ability attenuation of the trainee.

[0105] Wherein, the ability attenuation index is the degree of attenuation of the ability of the trainee predicted by the management platform based on the accumulated fatigue of the trainee and the basic attenuation coefficient of the new node.

[0106] wherein the basic attenuation coefficient is a coefficient corresponding to the node type, and the basic attenuation coefficient refers to the percentage of performance attenuation caused by unit cumulative fatigue on a node of a specific type. Therefore, the higher the basic attenuation coefficient, the greater the impact of fatigue on the corresponding type of node.

[0107] For example, 3 batches of trainees with cumulative fatigue indexes of 0.4, 0.5 and 0.6 respectively can be instructed to perform a precision equipment assembly task through experiments, and the average error rate of each batch of trainees can be obtained by counting the ratio of the average number of errors to the total number of actions of each batch of trainees. Then, the result of dividing the average error rate of each batch of trainees by the cumulative fatigue index corresponding to the trainee is taken as the basic attenuation coefficient of each batch of trainees. Then, the basic attenuation coefficients of each batch of trainees are fitted to obtain the basic attenuation coefficients of the precision equipment assembly nodes.

[0108] It can be understood that the average error rate is an attenuation calculation index of the precision equipment assembly node, and different attenuation calculation indexes can be adopted for other types of nodes. For example, the attenuation calculation index of the obstacle crossing node can be the unit distance time consumption growth rate, and the corresponding calculation formula is (actual unit distance time consumption - standard unit distance time consumption) / standard unit distance time consumption, wherein the standard unit distance time consumption is the average unit distance time consumption of the trainee in a non-fatigue state.

[0109] Specifically, the management platform can listen to node switching events, and in the case that the trainee enters a new area, submits an old task or starts timing of a new task, the management platform can obtain the ID of the second training node. Then, the basic attenuation coefficient of the second training node is obtained from the database.

[0110] Preferably, the management platform can obtain the recovery ability coefficient of the trainee, the environmental correction coefficient and the basic attenuation coefficient of the second training node; calculate the real-time attenuation coefficient based on the recovery ability coefficient, the environmental correction coefficient and the basic attenuation coefficient; and calculate the ability attenuation index based on the cumulative fatigue index and the real-time attenuation coefficient.

[0111] wherein the calculation formula of the real-time attenuation coefficient k includes:

[0112] ;

[0113] wherein, is the basic attenuation coefficient, is the recovery ability coefficient, is the deviation value when entering the second training node, is the historical maximum deviation value of the second training node, is the environmental correction coefficient.

[0114] For example, the basic attenuation coefficient of the high-precision shooting node is 1.8, the disassembling node of the explosive is 1.6, the load obstacle node is 1.3, the theoretical learning node is 1.0.

[0115] Specifically, the recovery ability coefficient is determined by the physical fitness and training level of the trainee, which can be set in the trainee's profile in the management platform after actual testing by the trainee; the management platform can obtain the recovery ability coefficient from the database.

[0116] Specifically, the environmental correction coefficient is a coefficient dynamically adjusted according to temperature, humidity and altitude. In harsh environments such as high temperature, high altitude and strong noise, the environmental correction coefficient is greater than 1, to describe the accelerated accumulation of fatigue of the trainee in harsh environments. The environmental correction coefficient can be obtained based on real-time temperature, pressure, noise sensor data and / or pre-configured node environment parameters.

[0117] Specifically, by calculating the ratio of the deviation value of the trainee entering the second training node and the historical maximum deviation value of the trainee, the load state of the trainee entering the second training node can be quantified.

[0118] Then, the management platform can calculate the ability attenuation index , the calculation formula includes:

[0119] ;

[0120] Wherein, the tanh() function can compress the output domain of the ability attenuation index to [0, 1], and adding a coefficient factor of 2.5 to the tanh() function can increase the steepness of the tanh() function, so that the input value can be mapped to the output close to the interval endpoint (0 or 1) in a narrower range, thereby strengthening the constraint effect on the result.

[0121] Step 204, in the case where the ability attenuation index is greater than a preset second threshold, the management platform sends a first call signal to the trainee terminal of the trainee.

[0122] Wherein, the first call signal is used to prompt the trainee to be in a fatigue state, and instruct the trainee to feed back the first call signal.

[0123] Exemplarily, the second threshold is 0.25.

[0124] It can be understood that the management platform can adjust the second threshold based on the environmental correction coefficient. Specifically, the environmental correction coefficient is negatively correlated with the second threshold.

[0125] Specifically, after receiving the first call signal, the trainee terminal can output a flashing light signal through the display screen, and prompt the trainee to take a break through the voice playing unit, and the trainee can feed back the first call signal through the touch screen, the key or the voice.

[0126] For example, the trainee terminal outputs a flashing yellow light signal based on the first call signal.

[0127] Step 205: When the trainee has no feedback and the training error at the second training node is greater than the ability attenuation index, the management platform sends a second call signal to the trainee terminal and a third call signal and alarm information to the trainer terminal.

[0128] The second call signal is used to instruct the trainee to pause training, the third call signal is used to instruct the trainer to assist the trainee, and the alarm information includes a traceability path report of the cumulative fatigue index of the trainee.

[0129] The training error refers to the percentage of deviation of the real-time training data of the trainee at the training node from the average of the historical training data.

[0130] The management platform can calculate the real-time training data of the trainee at the second training node through the feedback of the training equipment or the recognition of the training video stream collected by the photography equipment, calculate the average of the historical training data of the trainee at the second training node, then calculate the absolute value of the difference between the real-time training data and the average of the historical training data, and divide the absolute value of the difference by the average of the historical training data to obtain the percentage of deviation as the training error.

[0131] When the training error is greater than the ability attenuation index, it means that the current cumulative fatigue level of the trainee has been consistent with the prediction of the management platform, and the training needs to be paused or terminated to avoid safety accidents.

[0132] It can be understood that the training contents of different training nodes are different, and the ways of calculating the real-time training data and the average of the historical training data are different.

[0133] For example, when the second training node is a shooting node, the management platform can calculate the average number of shooting rings of the trainee at the second training node as the real-time training data, calculate the average number of historical shooting rings of the trainee at the second training node as the average of the historical training data, and then calculate the percentage of deviation based on the current average number of shooting rings and the average number of historical shooting rings to obtain the training error.

[0134] For example, when the second training node is an obstacle node, the management platform can calculate the time consumed by the trainee to reach the 1 / 3 position of the total distance in the second training node as real-time training data, calculate the historical average time consumed by the trainee to reach the 1 / 3 position of the total distance in the second training node as the historical training data mean, and then calculate the deviation percentage based on the time consumed by the trainee to reach the 1 / 3 position of the total distance in the current time and the historical average time, to obtain the training error.

[0135] Specifically, after receiving the second call signal, the trainee terminal can output a continuous light signal through the display screen, and alarm the trainee to pause training and rest immediately through the voice playing unit, and instruct the trainee to make a touch screen, key or voice feedback to the second call signal.

[0136] For example, the trainee terminal outputs a continuous red light signal based on the second call signal.

[0137] Preferably, in the case that the trainee has no feedback and the training error of the second training node is greater than the ability attenuation index, the management platform can issue a power-off instruction to the training equipment of the trainee, and the training equipment turns off the power of the training equipment itself based on the power-off instruction.

[0138] Specifically, after receiving the third call signal, the coach terminal drives the vibration motor of the coach terminal to continuously vibrate, and drives the buzzer of the coach terminal to continuously buzz alarm until the coach feeds back to the third call signal.

[0139] Specifically, the traceability path report includes a fatigue transmission path, a timeout contribution degree of a path node, and an environmental amplification factor; wherein the fatigue transmission path is used to locate the key node of fatigue generation, the timeout contribution degree is used to quantify the delay responsibility of each node, and the environmental amplification factor is used to indicate the influence of the external environment.

[0140] In the embodiment of the present application, in the case that the training time consumed by the trainee exceeds the time consumption baseline, the cumulative fatigue index is calculated based on the deviation between the timeout amplitude, the physiological data and the physiological baseline, and the fatigue transmission coefficient between the training nodes, which can quantify the risk of the fatigue accumulated by the trainee; then the training error is calculated to measure the conversion tendency of the risk, and a call signal is issued based on the conversion tendency to alarm. By using the embodiment of the present application, the safety risk of fatigue accumulation of the trainee in the training process can be accurately identified, and timely alarm can be given.

[0141] As shown in Figure 3 Figure 3 ​A possible logical structure diagram of a computing device provided for the embodiments of the present application. The computing device 300 comprises a processor 301, a communication interface 302, a memory 303 and a bus 304, the processor 301, the communication interface 302 and the memory 303 are connected with each other through the bus 304. In the embodiments of the present application, the processor 301 is configured to control and manage the actions of the computing device 300, for example, the processor 301 is configured to execute the program codes stored in the memory 303 to perform the steps of the embodiments of the present application. Figure 2 The steps in the embodiments and / or other processes for the techniques described herein. The communication interface 302 is configured to support the communication of the computing device 300. The memory 303 is configured to store the program codes and data of the computing device 300.

[0142] The processor 301 can be a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute the various exemplary logical blocks, modules and circuits described in connection with the disclosure. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of digital signal processors and microprocessors, etc. The bus 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For the convenience of representation, Figure 3 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0143] In another embodiment of the present application, a computer readable storage medium is also provided, the computer readable storage medium comprises instructions, when the instructions are run on a computer, the computer executes the method described in the above Figure 2 Embodiments.

[0144] Those of ordinary skill in the art can realize that the units of each example described in connection with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components of each example have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0146] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0147] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0148] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0149] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various storage media that can store program codes.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and the description of the present application.

Claims

1. A training fatigue accumulation warning method, characterized in that: The method comprises: Obtaining the trainee's real-time elapsed time, real-time physiological data, and personal baseline at the first training node, the personal baseline including a physiological baseline and a time-consuming baseline. The physiological baseline is calculated based on the trainee's historical physiological data during training at the first training node, and the time-consuming baseline is calculated based on the average historical elapsed time for the trainee to complete the first training node. The historical physiological data includes historical heart rate and historical blood oxygen levels. When the difference between the real-time consumption and the time-consuming baseline is greater than a preset first threshold, the cumulative fatigue index of the trainee at the first training node is calculated based on the deviation value, the fatigue conduction coefficient, and the node timeout amplitude; wherein the deviation value is used to indicate the deviation between the real-time physiological data and the physiological baseline, the node timeout amplitude is calculated based on the difference between the real-time consumption and the time-consuming baseline, and the time-consuming baseline, and the fatigue conduction coefficient is used to indicate the fatigue influence weight of the previous node on the next node in the training process; The calculation formula of the cumulative fatigue index includes: ； in, is the cumulative fatigue index of the previous node, is the current deviation value, is the fatigue transfer coefficient of the previous node i to the current node j; K is the overtime fatigue gain index, is the node timeout amplitude; if the previous node is the first node, then is 0; When the trainee enters a second training node, calculating the trainee's ability decay index based on the trainee's cumulative fatigue index at the first training node; wherein the second training node is a node subsequent to the first training node; The calculation formula of the capacity decay index includes: ； ； Where k is the real-time attenuation coefficient, is the basic attenuation coefficient of the second training node, is the student's recovery coefficient, is the deviation value when the student enters the second training node, is the historical maximum deviation value of the second training node, is the environmental correction factor; When the ability decay index is greater than a preset second threshold, sending a first call signal to the trainee terminal of the trainee, wherein the first call signal is used to prompt the trainee that the trainee is in a fatigue state and instruct the trainee to provide feedback on the first call signal; When the student has no feedback and the training error at the second training node is greater than the ability decay index, a second call signal is sent to the student terminal, and a third call signal and an alarm message are sent to the coach terminal; wherein, the second call signal is used to instruct the student to suspend training, the third call signal is used to instruct the coach to assist the student, and the alarm message includes a traceability path report of the student's cumulative fatigue index.

2. The method according to claim 1, characterized in that In a case where the trainee has no feedback and the training error at the second training node is greater than the ability decay index, the method further includes: Sending a power-off instruction to the trainee's training device, wherein the power-off instruction is used to instruct the training device to turn off the power supply of the training device itself; The third call signal is further used to instruct the coach terminal to drive the vibration motor of the coach terminal to vibrate continuously until the coach gives feedback to the third call signal.

3. The method according to claim 1 or 2, characterized in that Before calculating the cumulative fatigue index of the trainee at the first training node based on the deviation value, the fatigue transfer coefficient, and the node timeout amplitude, the method further includes: Obtaining the student's physical fitness level factor, preset attenuation coefficient, and node type correction coefficient; The fatigue transfer coefficient is calculated based on the node type correction coefficient between the first training node and the second training node, the physical fitness level factor, and the attenuation coefficient.

4. The method according to claim 3, characterized in that The deviation value includes a first deviation value and a second deviation value; after calculating the cumulative fatigue index of the trainee at the first training node based on the deviation value, the fatigue transfer coefficient, and the node timeout amplitude, the method further includes: Obtaining the first deviation value after the trainee completes the first training node, and the second deviation value after the trainee completes a third training node; wherein the third training node is a node preceding the first training node; The fatigue transmission coefficient is updated based on the first deviation value and the second deviation value.

5. The method according to claim 1 or 2, characterized in that After the trainee completes the first training node, the method further includes: Obtain the average time taken by the student to complete the first training node for the last N times, where N is less than the total number of times the student completes the first training node; Based on the average time consumption, the time consumption baseline is updated.

6. A training fatigue accumulation warning system, characterized in that: The method according to any one of claims 1 to 5, wherein the system comprises a management platform, a coach terminal and a trainee terminal; The management platform is used to obtain the trainee's real-time time consumption, real-time physiological data and personal baseline at the first training node, wherein the personal baseline includes a physiological baseline and a time consumption baseline. The physiological baseline is calculated based on the trainee's historical physiological data when training at the first training node, and the time consumption baseline is calculated based on the historical average time consumption of the trainee to complete the first training node; the historical physiological data includes historical heart rate and historical blood oxygen; In the case where the difference between the real-time consumption and the time-consuming baseline is greater than a preset first threshold, the management platform is further configured to calculate the cumulative fatigue index of the trainee at the first training node based on the deviation value, the fatigue conduction coefficient, and the node timeout amplitude; wherein the deviation value is used to indicate the deviation between the real-time physiological data and the physiological baseline, the node timeout amplitude is calculated based on the difference between the real-time consumption and the time-consuming baseline, and the time-consuming baseline, and the fatigue conduction coefficient is used to indicate the fatigue influence weight of a previous node on a subsequent node in the training process; The calculation formula of the cumulative fatigue index includes: ； in, is the cumulative fatigue index of the previous node, is the current deviation value, is the fatigue transfer coefficient of the previous node i to the current node j; K is the overtime fatigue gain index, is the node timeout amplitude; if the previous node is the first node, then is 0; When the trainee enters a second training node, the management platform is further configured to calculate the trainee's ability decay index based on the trainee's cumulative fatigue index at the first training node; wherein the second training node is a node subsequent to the first training node; The calculation formula of the capacity decay index includes: ； ； Where k is the real-time attenuation coefficient, is the basic attenuation coefficient of the second training node, is the student's recovery coefficient, is the deviation value when the student enters the second training node, is the historical maximum deviation value of the second training node, is the environmental correction factor; When the ability decay index is greater than a preset second threshold, the management platform is further configured to send a first call signal to the trainee terminal of the trainee, wherein the first call signal is configured to prompt the trainee that the trainee is in a fatigue state and instruct the trainee to provide feedback on the first call signal; When the student has no feedback and the training error at the second training node is greater than the ability decay index, the management platform is also used to send a second call signal to the student terminal and send a third call signal and alarm information to the coach terminal; wherein, the second call signal is used to instruct the student to suspend training, the third call signal is used to instruct the coach to assist the student, and the alarm information includes a traceability path report of the student's cumulative fatigue index.

7. A computing device, characterized in that include: Memory, used to store programs; A processor, configured to load the program to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

Images