CN116548970A

CN116548970A - State studying and judging method and device for deep-open sea operators

Info

Publication number: CN116548970A
Application number: CN202310535483.4A
Authority: CN
Inventors: 张玉乾; 付永江; 张玉麟; 彭玉娇; 程婕; 崔婧; 牛嵩云; 程远
Original assignee: China Shipbuilding Human Factors Engineering Research Institute Qingdao Co ltd
Current assignee: China Shipbuilding Human Factors Engineering Research Institute Qingdao Co ltd
Priority date: 2023-05-12
Filing date: 2023-05-12
Publication date: 2023-08-08

Abstract

The invention discloses a state studying and judging method and device for deep-open sea operators, wherein the method comprises the following steps: collecting physiological data, behavior data and environmental data of an operator in an environment; extracting statistical characteristics of physiological data, behavior data and environmental data, and carrying out normalization processing on the statistical characteristics; inputting the normalized statistical features into a hidden layer of an LSTM network, and carrying out weighted summation on different statistical features by adopting an attention mechanism to obtain a final feature vector; and inputting the final feature vector into a softmax layer to obtain a classification result of the physical and mental states of the operator. According to the invention, through establishing the association relation between the physiological, behavioral and environmental data of the deep-sea operators, the operation fatigue, the operation pressure and the negative emotion, the accurate study and judgment of the physical and psychological states of the operators are realized.

Description

State studying and judging method and device for deep-open sea operators

Technical Field

The invention relates to the technical field of data processing, in particular to a state studying and judging method and device for deep-open sea operators.

Background

The life and work of the deep-open sea operators are separated from the continent for a long time, and the special working environment and task with high temperature and high humidity increase the occurrence probability of physical and psychological states of the operators such as operation fatigue, operation pressure, negative emotion and the like; firstly, with the increase of age, the increase of workload and the influence of basic diseases or other health problems, the sudden abnormality or diseases of physical conditions of operators are easily caused in the operation process; secondly, the mental state of the operators is easy to be abnormal due to working strength, social working relation or other factors, and negative emotions such as fear, anger, sadness, aversion and the like are generated, or the mental fatigue is mainly generated and the central nervous system fatigue is caused, so that the operators are in the mental state of distraction, negative lassitude and low alertness. The negative physical and psychological state can increase the probability of safety production accidents, cause disability and sudden death of operators, and have irrecoverable consequences. Developing the study and judgment of the physical and psychological states of operators is an important study subject in the field of health and medical electronics.

The traditional subjective report and scale evaluation mode can not accurately capture the physical and psychological states of operators in real time, and objective monitoring evaluation can not be carried out; the existing medical-grade equipment has the functions of acquiring and monitoring basic physiological indexes such as heart rate and blood pressure, but the corresponding scenes are not shifted from generalized working and living scenes to special task operation scenes such as deep open sea, and an effective and high-portability integrated solution for researching and judging the physical and psychological states of operators is not proposed.

Disclosure of Invention

Aiming at the technical problem that the prior art cannot accurately and effectively evaluate the physical and mental states of operators in special working scenes such as deep open sea, the invention provides a state studying and judging method and device for deep open sea operators.

In a first aspect, an embodiment of the present application provides a method for determining a status of a deep open sea worker, including:

and a data acquisition step: collecting physiological data, behavior data and environmental data of an operator in an environment;

and a feature extraction step: extracting statistical features of the physiological data, the behavior data and the environmental data, and carrying out normalization processing on the statistical features;

and a feature weighting step: inputting the normalized statistical features into a hidden layer of an LSTM network, and carrying out weighted summation on different statistical features by adopting an attention mechanism to obtain a final feature vector;

a physical and mental state classification step: and inputting the final feature vector into a softmax layer to obtain a classification result of the physical and mental states of the operator.

The state research and judgment method further comprises the following steps:

database establishment: and establishing a physical and mental state database of the operator based on the physiological data, the behavior data and the environmental data of the operator in the resting state and the operating state respectively.

The state studying and judging method, wherein the step of classifying the physical and psychological states further comprises the following steps: training the softmax layer based on the physical and mental state database and searching for optimal parameters.

The state research and judgment method, wherein the feature extraction step comprises the following steps:

and a time domain feature extraction step: extracting basic statistical features and time domain features of the physiological data, the behavior data and the environmental data;

a frequency domain feature obtaining step: performing time-frequency conversion on the time domain features of the physiological data to obtain frequency domain features of the physiological data;

normalization: and normalizing the basic statistical features, the time domain features and the frequency domain features to obtain normalized statistical features.

The state research and judgment method, wherein the time domain feature extraction step comprises the following steps:

pretreatment: preprocessing the collected physiological data, the behavior data and the environment data;

a signal period obtaining step: identifying the preprocessed physiological data through a feature point extraction algorithm to obtain a physiological signal period of the physiological data;

basic statistical feature extraction: and extracting basic statistical characteristics of the physiological data, the behavior data and the environment data based on the physiological signal period.

The state research and judgment method, wherein the classification result of the physical and psychological state comprises the following steps: the level of working pressure, working fatigue and working negative emotion of the working personnel.

In a second aspect, an embodiment of the present application provides a state studying and judging device for a deep open sea operator, configured to implement the state studying and judging method described in the first aspect, including:

and a database building module: establishing a physical and psychological state database of the operator based on physiological data, behavioral data and environmental data of the operator in a resting state and an operating state respectively;

and a data acquisition module: collecting physiological data, behavior data and environmental data of an operator in an environment;

and the feature extraction module is used for: extracting statistical features of the physiological data, the behavior data and the environmental data, and carrying out normalization processing on the statistical features;

and a feature weighting module: inputting the normalized statistical features into a hidden layer of an LSTM network, and carrying out weighted summation on different statistical features by adopting an attention mechanism to obtain a final feature vector;

the physical and mental state classification module: and inputting the final feature vector into a softmax layer to obtain a classification result of the physical and mental states of the operator.

The state research and judgment device, wherein the data acquisition module comprises:

the environment data acquisition unit is used for acquiring environment data of the environment where the operator is located, and comprises a temperature sensor, a humidity sensor and an air pressure sensor;

the physiological data acquisition unit is used for acquiring physiological data of operators, and the physiological data acquisition unit comprises: heart rate/pulse sensors, blood oxygen sensors, skin resistance sensors, and skin temperature sensors;

the behavior data acquisition unit is used for acquiring behavior data of operators and comprises an accelerometer, a gyroscope and a magnetometer.

The state research and judgment device, wherein the feature extraction module comprises:

time domain feature extraction unit: extracting basic statistical features and time domain features of the physiological data, the behavior data and the environmental data;

frequency domain feature obtaining unit: performing time-frequency conversion on the time domain features of the physiological data to obtain frequency domain features of the physiological data;

normalization unit: and normalizing the basic statistical features, the time domain features and the frequency domain features to obtain normalized statistical features.

The state research and judgment device, wherein the feature extraction module further comprises:

the data preprocessing unit is used for preprocessing the physiological data, the behavior data and the environmental data acquired by the data acquisition module, and comprises an A/D converter and a digital filter, wherein the A/D converter is used for converting the physiological data, the behavior data and the environmental data acquired by the data acquisition module into digital signals from analog signals, and the digital filter is used for carrying out primary noise reduction processing on the digital signals.

Compared with the prior art, the invention has the advantages and positive effects that:

based on the characteristics of being widely available in deep-open sea ships, working platforms and the like, such as being far away from land, high in temperature, high in humidity, high in working strength and the like, the invention establishes the physiological and behavioral data, the environmental data, the working fatigue, the working pressure and the negative emotion association relation of the deep-open sea working personnel through establishing the deep-open sea working personnel physical and mental state database, designing the feature selection and deep learning algorithm, realizes the accurate study and judgment of the multi-dimensional physical and mental states of personnel basic activity, basic vital signs, working pressure and working fatigue, solves the problems that the physical and mental states of the deep-open sea working personnel cannot be effectively studied and judged, and is low in portability, forms an integrated solution, and realizes the accurate monitoring and real-time guarantee of the physical and mental states of the working personnel.

Drawings

FIG. 1 is a schematic diagram of the method for determining the status of a deep-sea worker according to the present invention;

fig. 2 is a schematic flow chart based on step S3 in fig. 1 according to the present invention;

fig. 3 is a schematic flow chart based on step S31 in fig. 2 according to the present invention;

FIG. 4 is a flowchart illustrating an embodiment of a method for determining status of a deep ocean worker according to the present invention;

fig. 5 is a schematic structural diagram of a state studying and judging device for deep-open sea operators provided by the invention;

fig. 6 is a schematic diagram of an embodiment of a status studying and judging device for deep-sea operators according to the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described and illustrated below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden on the person of ordinary skill in the art based on the embodiments provided herein, are intended to be within the scope of the present application.

It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the embodiments described herein can be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar terms herein do not denote a limitation of quantity, but rather denote the singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein refers to two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.

The present invention will be described in detail below with reference to the embodiments shown in the drawings, but it should be understood that the embodiments are not limited to the present invention, and functional, method, or structural equivalents and alternatives according to the embodiments are within the scope of protection of the present invention by those skilled in the art.

Before explaining the various embodiments of the invention in detail, the core inventive concepts of the invention are summarized and described in detail by the following examples.

According to the invention, through establishing the physical and psychological state database of the deep-sea operation personnel, designing the feature selection and deep learning algorithm, and establishing the association relationship between the physiological, behavioral and environmental data of the deep-sea operation personnel, the operation fatigue, the operation pressure and the negative emotion, the precise study and judgment of the physical and psychological states of the operation personnel are realized.

Embodiment one:

fig. 1 is a schematic diagram of steps of a state studying and judging method for deep-open sea operators provided by the invention. As shown in fig. 1, the present embodiment discloses a specific embodiment of a method for determining the status of a deep-open sea operator (hereinafter referred to as "method").

Specifically, the method disclosed in this embodiment mainly includes the following steps:

step S1: establishing a physical and psychological state database of the operator based on physiological data, behavioral data and environmental data of the operator in a resting state and an operating state respectively;

specifically, the physical and mental state database comprises a baseline data set of an operator in a resting state and a physical and mental state data set of the operator in the operating state; the baseline data set refers to the time when the operator is at rest in a resting state (non-operating state) and in a normal environment: physiological data including pulse, blood oxygen, skin resistance, skin temperature, etc., corresponding operation environment data, activity data, etc.; the physical and mental state data set refers to the situation that an operator is in a real operation scene, a simulated pressure, a simulated fatigue and a negative emotion induction state: includes physiological data such as pulse, blood oxygen, skin resistance, skin temperature, etc., corresponding operation environment data, activity data, etc.

Step S2: collecting physiological data, behavior data and environmental data of an operator in an environment;

specifically, the original physiological data, behavior data and environmental data of the environment where the worker is located are collected through a data collection module; physiological data includes data such as heart rate/pulse, skin resistance and body temperature of the worker; the behavior data comprise data such as the activity degree and the gesture of the operator; the environmental data includes temperature, humidity, air pressure, etc. of the external environment in which the worker is located.

Step S3: extracting statistical features of the physiological data, the behavior data and the environmental data, and carrying out normalization processing on the statistical features;

as shown in fig. 2, step S3 includes:

step S31: extracting basic statistical features and time domain features of the physiological data, the behavior data and the environmental data;

further, as shown in fig. 3, step S31 includes:

step S311: preprocessing the collected physiological data, the behavior data and the environment data; wherein the preprocessing includes noise removal by filtering, smoothing, baseline calibration, etc.

Step S312: identifying the preprocessed physiological data through a feature point extraction algorithm to obtain a physiological signal period of the physiological data;

step S313: and extracting basic statistical characteristics of the physiological data, the behavior data and the environment data based on the physiological signal period.

Step S32: performing time-frequency conversion on the time domain features of the physiological data to obtain frequency domain features of the physiological data; the time domain features of the physiological data in the present embodiment include time domain features of heart rate variability, skin conductance response, and the like.

Step S33: and normalizing the basic statistical features, the time domain features and the frequency domain features to obtain normalized statistical features.

Step S4: inputting the normalized statistical features into a hidden layer of an LSTM network, and carrying out weighted summation on different statistical features by adopting an attention mechanism to obtain a final feature vector;

all basic statistical characteristics, time domain characteristics and frequency domain characteristics are converted into numerical values between 0 and 1 through standardized treatment, and the numerical values are unified in dimension; in step S4, the physiological, behavioral and environmental features are outputted through the hidden layer of the double-layer long-short-term memory network (LSTM) and then fused to form a new feature map, and further, as different hidden states have different degrees of contribution and influence on the operation fatigue, the operation pressure and the negative emotion, the attention mechanism assigns different weights to different statistical features to form a plurality of weighted sums of the hidden states as final feature vectors. For example, three hidden layers are set for the operation pressure, a larger weight is given to heart rate variability characteristics, two hidden layers are set for negative emotion, a larger weight is given to galvanic skin characteristics, and the layer number and the weight with the best recognition effect can be determined through the training of an algorithm and the parameter optimizing process.

Step S5: and inputting the final feature vector into a softmax layer to obtain a classification result of the physical and mental states of the operator. The classification result of the physical and mental states comprises: the working pressure, working fatigue and working negative emotion level of the working personnel are, for example, high, medium and low, wherein the high, medium and low levels are classified according to the marked labels in the data set and are calibrated by means of psychological scales and expert evaluation.

Further, step S5 further includes: training the softmax layer based on the physical and mental state database and searching for optimal parameters. In specific implementation, the baseline data set in the rest state can be subtracted from the physical and mental state data set collected in the working state in the physical and mental state database, and then the physical and mental state data set is input into the classification model for algorithm training and parameter optimizing.

Next, please refer to fig. 4. FIG. 4 is a flowchart illustrating an embodiment of a method for determining status of a deep ocean worker according to the present invention; referring to fig. 4, the application flow of the method is specifically described as follows:

1. establishing a physical and psychological state database of deep-open sea operators;

the physical and mental state database comprises: the method comprises the steps of setting a baseline data set of an operator in a resting state and a physical and mental state data set of the operator in a real operation scene, a simulated pressure, a simulated fatigue and a negative emotion induction state, wherein the baseline data set and the physical and mental state data set comprise: includes physiological data such as pulse, blood oxygen, skin resistance, skin temperature, etc., corresponding operation environment data, activity data, etc.

2. Extracting characteristics in real time;

firstly, preprocessing collected original physiological data, behavior data and environmental data through operations such as filtering, smoothing, baseline calibration and the like, identifying physiological signal periods of the preprocessed physiological data through a feature point extraction algorithm, and then extracting basic statistical features of the original physiological data, the environment data and the behavior data in each physiological signal period, such as a PPG period, extracting the amplitude, rising time, falling time and the like of a complete PPG waveform;

further, decomposition and extraction are carried out on the basis of original physiological, environmental and behavioral data to obtain heart rate variability, skin conductance response and other time domain characteristics, for example, an original PPG signal is converted into a heart rate variation signal, and then the time domain characteristics of the heart rate variability are extracted; decomposing the original skin electric signal into skin conductance reaction and skin conductance level, and extracting time domain characteristics;

further, time-frequency conversion is carried out on the time domain features of the original physiological data to extract frequency domain features, and finally, normalization processing is carried out on the basic statistical features of all physiological, behavioral and environmental data and all extracted time domain features and frequency domain features, namely, normalization processing is carried out on all features, and the features are transformed into numerical values between 0 and 1, so that the dimension is unified.

3. Feature selection and physical and mental state classification are realized through a double-layer long and short-term memory network (LSTM) and an attention mechanism;

inputting the normalized physiological, behavioral and environmental characteristics into a hidden layer of an LSTM, outputting and then fusing to form a new characteristic map, and distributing different weights to different characteristics by adopting an attention mechanism because different hidden states have different degrees of contribution and influence on operation fatigue, operation pressure and negative emotion to form a final characteristic vector input Softmax layer of a plurality of weighted sums of the hidden states; for example, three hidden layers are set for the working pressure, a larger weight is given to heart rate variability characteristics, two hidden layers are set for negative emotion, a larger weight is given to galvanic skin characteristics, and the layer number and the weight with the best recognition effect can be determined through the training of an algorithm and the parameter optimizing process. Finally, training and parameter optimizing are carried out on the classification algorithm (Softmax layer) based on the body and mind state database of the deep-open sea operator, so that the classification of the high, middle and low levels of different body and mind states is realized.

The embodiment is based on the characteristics of being widely provided with a deep open sea ship, an operation platform and the like, such as being far away from land, high temperature, high humidity, high working strength and the like, analyzes the influence of special environments and task operation scenes on the physical and mental states of personnel, realizes the accurate study and judgment of the multi-dimensional physical and mental states of basic activity, basic vital signs, operation pressure and operation fatigue of the personnel, and forms an integrated solution.

Embodiment two:

in combination with the method for determining the status of the deep-sea operator disclosed in the first embodiment, the embodiment discloses a specific implementation example of a device for determining the status of the deep-sea operator (hereinafter referred to as "device").

Referring to fig. 5, the apparatus includes:

database creation module 1: establishing a physical and psychological state database of the operator based on physiological data, behavioral data and environmental data of the operator in a resting state and an operating state respectively;

data acquisition module 2: collecting physiological data, behavior data and environmental data of an operator in an environment;

specifically, the data acquisition module 2 includes:

an environmental data acquisition unit 21 for acquiring environmental data of an environment in which an operator is located, the environmental data acquisition unit including a temperature sensor, a humidity sensor, and an air pressure sensor;

a physiological data acquisition unit 22 for acquiring physiological data of an operator, the physiological data acquisition unit comprising: heart rate/pulse sensors, blood oxygen sensors, skin resistance sensors, and skin temperature sensors;

and the behavior data acquisition unit 23 is used for acquiring the behavior data of the operator, and comprises an accelerometer, a gyroscope and a magnetometer.

Feature extraction module 3: extracting statistical features of the physiological data, the behavior data and the environmental data, and carrying out normalization processing on the statistical features;

specifically, the feature extraction module 3 includes:

the data preprocessing unit 31 is configured to preprocess the physiological data, the behavioral data and the environmental data acquired by the data acquisition module, where the data preprocessing unit includes an a/D converter and a digital filter, the a/D converter is configured to convert the physiological data, the behavioral data and the environmental data acquired by the data acquisition module from analog signals to digital signals, and the digital filter is configured to perform primary noise reduction processing on the digital signals.

Time domain feature extraction unit 32: extracting basic statistical features and time domain features of the physiological data, the behavior data and the environmental data;

further, the time domain feature extraction unit 32 includes:

signal period obtaining unit 321: identifying the preprocessed physiological data through a feature point extraction algorithm to obtain a physiological signal period of the physiological data;

basic statistical feature extraction unit 322: basic statistical features of the physiological data, the behavioral data, and the environmental data are extracted based on the physiological signal period.

Frequency domain feature obtaining unit 33: performing time-frequency conversion on the time domain features of the physiological data to obtain frequency domain features of the physiological data;

normalization unit 34: and normalizing the basic statistical features, the time domain features and the frequency domain features to obtain normalized statistical features.

Feature weighting module 4: inputting the normalized statistical features into a hidden layer of an LSTM network, and carrying out weighted summation on different statistical features by adopting an attention mechanism to obtain a final feature vector;

physical and mental state classification module 5: and inputting the final feature vector into a softmax layer to obtain a classification result of the physical and mental states of the operator. The classification result of the physical and mental states comprises: the level of working pressure, working fatigue and working negative emotion of the working personnel.

Wherein, the physical and mental state classification module 5 is further used for: training the softmax layer based on the physical and mental state database and searching for optimal parameters.

Next, please refer to fig. 6. FIG. 6 is a schematic diagram of an embodiment of a status studying and judging device for deep-sea workers according to the present invention; the device can be a wearable bracelet, can acquire human physiology, behavior and environmental data, and specifically comprises heart rate, blood oxygen, skin resistance, skin temperature, activity, gesture, environmental temperature, environmental humidity, environmental air pressure and other index data, so as to assist in studying and judging physical and psychological states and solve the problems of insufficient index integration level and low portability of the traditional product.

Referring to fig. 6, the structure of the present device specifically includes:

the environment data acquisition unit comprises a temperature sensor, a humidity sensor, an air pressure sensor and the like, and is used for acquiring environment data such as temperature, humidity, air pressure and the like of the external environment where personnel are located, and the environment data are stored in the data storage unit or are transmitted through the data transmission unit after being transmitted to the data preprocessing unit through the electric signal for analysis and processing under the control of the control unit, so that the monitoring of the external environment data where personnel are located is realized;

the physiological data acquisition unit comprises a heart rate/pulse sensor, a blood oxygen sensor, a skin resistance sensor and a skin temperature sensor, and is used for acquiring physiological data such as heart rate/pulse, skin resistance and body temperature of a person, and the physiological data is stored in the data storage unit or is transmitted through the data transmission unit after being transmitted to the data preprocessing unit for analysis and processing under the control of the control unit, so that the physiological data of the person is monitored;

the behavior data acquisition unit comprises an accelerometer, a gyroscope and a magnetometer and is used for acquiring behavior data such as the activity degree and the gesture of a person, and the behavior data is stored in the data storage unit or transmitted through the data transmission unit after being transmitted to the data preprocessing unit through an electric signal for analysis and processing under the control of the control unit, so that the monitoring of the behavior data of the person is realized;

the sensor realizes multi-mode and high-precision acquisition, can acquire physiological, behavioral and environmental data, and comprises heart rate, blood oxygen, skin resistance, skin temperature, activity, gesture, environment temperature, environment humidity, environment air pressure and other index data, wherein the skin resistance and the skin temperature are important indexes essential for studying and judging physical and psychological states, the acquisition precision of the skin resistance can reach 0.01 mu s, and the accuracy of auxiliary studying and judging is improved.

The identity recognition unit is used for rapidly recognizing and registering the identity information of the personnel;

the reminding unit comprises a functional lamp and a vibration motor and is used for reminding a person of the data acquisition state of the bracelet and the working states of electric quantity, wireless connection, data transmission, memory and the like;

the control unit comprises a singlechip MCU, realizes the control of the identity recognition unit, the environment data acquisition unit, the physiological data acquisition unit, the behavior data acquisition unit, the data preprocessing unit and the reminding unit through an algorithm program, and realizes the orderly, automatic and continuous action of each unit;

a power supply unit for supplying power to the state judging device;

the data preprocessing unit comprises an A/D converter (ADC) and a digital filter, and is used for converting acquired physiological, behavioral and environmental data from analog signals to digital signals and performing primary noise reduction processing;

the data storage unit comprises a storage module and a data transmission unit, wherein the storage module is used for storing the preprocessed physiological, behavioral and environmental data, and the physiological, behavioral and environmental data are transmitted to the data transmission unit through the data transmission unit when the wireless data network is accessed;

the data transmission unit comprises modules such as Bluetooth, wiFi, serial ports and the like and is used for uploading the stored preprocessed personnel physiological, behavior and environment data to the management terminal or the database in a wired, wireless or other mode for sharing, and the data transmitted by the data transmission unit come from two different channels of the data preprocessing unit and the data storage unit; therefore, the bracelet working modes in the embodiment are divided into 2 modes, the first mode is a real-time mode, and the acquired data is uploaded in real time through Bluetooth/WiFi; the second mode is an offline mode, collected data are stored in the bracelet locally, and after the collection is finished, the local data are exported and uploaded through a USB wired encryption transmission mode.

The physical and mental state research and judgment unit comprises a management terminal and a database, performs physical and mental state research and judgment based on the management terminal and the database (physical and mental state database), and can also issue a control instruction by the management terminal for controlling the control unit.

The technical scheme of the state studying and judging device for the deep-sea operator disclosed in the present embodiment and the rest of the same parts in the state studying and judging method for the deep-sea operator disclosed in the first embodiment are described in the first embodiment, and are not repeated here.

Aiming at the physical and psychological states which are easy to appear and influence the working efficiency of deep and open sea operators, the invention provides a method for accurately studying and judging the multi-dimensional physical and psychological states of basic activity, basic vital signs, working pressure and working fatigue and a device for studying and judging the physical and psychological states. The problems that the physical and psychological states of deep-open sea operators cannot be effectively researched and judged and portability is low are solved, an integrated solution is formed, and accurate monitoring and real-time guarantee of the physical and psychological states of the operators are achieved.

The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. The state research and judgment method for the deep-open sea operators is characterized by comprising the following steps of:

2. The state studying and judging method of claim 1, further comprising:

3. The state studying and judging method of claim 2, wherein the body and mind state classifying step further comprises: training the softmax layer based on the physical and mental state database and searching for optimal parameters.

4. The state studying and judging method of claim 1, wherein the feature extracting step comprises:

5. The state studying and judging method of claim 4, wherein the time domain feature extracting step comprises:

6. The state studying and judging method of claim 1, wherein the classification result of the physical and mental states comprises: the level of working pressure, working fatigue and working negative emotion of the working personnel.

7. A state research and judgment device for deep-sea operators, for implementing the state research and judgment method according to any one of claims 1-6, comprising:

8. The state studying device of claim 7, wherein the data acquisition module comprises:

9. The state studying apparatus of claim 7, wherein the feature extraction module comprises:

10. The state research apparatus of claim 9, wherein the feature extraction module further comprises: