CN117594242B - Human body fatigue evaluation optimization method, device, equipment and storage medium - Google Patents

Human body fatigue evaluation optimization method, device, equipment and storage medium Download PDF

Info

Publication number
CN117594242B
CN117594242B CN202410077649.7A CN202410077649A CN117594242B CN 117594242 B CN117594242 B CN 117594242B CN 202410077649 A CN202410077649 A CN 202410077649A CN 117594242 B CN117594242 B CN 117594242B
Authority
CN
China
Prior art keywords
data
load index
physiological
determining
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410077649.7A
Other languages
Chinese (zh)
Other versions
CN117594242A (en
Inventor
王柏村
卓正阳
杨振
严浩
郑宗波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202410077649.7A priority Critical patent/CN117594242B/en
Publication of CN117594242A publication Critical patent/CN117594242A/en
Application granted granted Critical
Publication of CN117594242B publication Critical patent/CN117594242B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
    • A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Physiology (AREA)
  • Dentistry (AREA)
  • Psychiatry (AREA)
  • Cardiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Child & Adolescent Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Educational Technology (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychology (AREA)
  • Social Psychology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The application provides a human body fatigue evaluation optimization method, a device, equipment and a storage medium. The human body fatigue evaluation optimization method provided by the application comprises the following steps: collecting working posture data, physiological data and subjective evaluation data; splitting the working posture data into sub-working posture data according to the working posture, and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data; correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index; and calculating the fatigue degree of the human body. The human body fatigue evaluation optimization method, the device, the equipment and the storage medium can realize comprehensive, accurate and rapid evaluation of human body fatigue.

Description

Human body fatigue evaluation optimization method, device, equipment and storage medium
Technical Field
The application relates to the technical field of fatigue monitoring, in particular to a human body fatigue evaluation optimization method, device, equipment and storage medium.
Background
In the field of manufacturing systems and labor tasks, assessment of human fatigue is of great importance, as it relates to the health and work safety of the workers. However, existing human fatigue assessment methods present many challenges in coping with the diversity of labor tasks and providing accurate assessment.
Firstly, the existing human body fatigue evaluation methods at home and abroad have a certain limit on the application range, and are generally only suitable for specific types of work, which limits the universality of practical application. Furthermore, the quantitative indicators used in these methods are different, resulting in difficulties in comparison and standardization between different studies and applications. Secondly, the reasons for selecting the indexes often lack sufficient scientific basis, which reduces the scientificity and accuracy of human fatigue assessment. Meanwhile, the proposed operation improvement method often lacks feasibility or is not verified experimentally, which affects the feasibility and effectiveness of the operation improvement method in practical application. Furthermore, for low load work, the assessment method may be susceptible to interference from individual high risk actions, resulting in distortion of the final score. Gesture risk assessment methods typically ignore the impact of the frequency of motion in multi-gesture work on overall gesture risk, which may lead to inaccurate assessment. Finally, existing methods require a significant amount of time to analyze and calculate the data in the face of highly repetitive work, and lack suitable computational simplification methods, thus complicating and rendering impractical the study.
In the prior art, because the research of a single signal can lead to low evaluation accuracy, a mode of comprehensively and accurately evaluating the signal by utilizing the signals with multiple dimensions is generally adopted, but the mode needs the data with the multiple dimensions to fuse the data and the judgment result, a large number of calculation processes are generally needed, the accuracy of fatigue judgment cannot be ensured, and meanwhile, the calculation time is long and the efficiency is low.
Disclosure of Invention
In view of the above, the present application provides a method, apparatus, device and storage medium for optimizing human fatigue evaluation, so as to implement comprehensive, accurate and rapid evaluation of human fatigue.
Specifically, the application is realized by the following technical scheme:
the first aspect of the application provides a human body fatigue evaluation optimization method, which comprises the following steps:
collecting working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprise two types of data;
splitting the working posture data into sub-working posture data according to the working posture, and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data;
Correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index;
calculating the fatigue of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
the correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
Identifying an error probability for an error feature range based on the correction feature range;
and based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as the target data corresponding to the corrected physiological load index.
A second aspect of the present application provides a human fatigue evaluation optimization device, the device comprising an acquisition module, a processing module and a calculation module, wherein,
the acquisition module is used for acquiring working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprises two types of data;
the processing module is used for splitting the working posture data into sub-working posture data according to the working posture and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data;
the calculation module is used for correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index;
The calculation module is further used for calculating the fatigue degree of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
the correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
Identifying an error probability for an error feature range based on the correction feature range;
and based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as the target data corresponding to the corrected physiological load index.
A third aspect of the present application provides a human fatigue assessment optimization device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any one of the methods provided in the first aspect of the present application when the program is executed.
A fourth aspect of the present application provides a storage medium having stored thereon a program which when executed by a processor performs the steps of any of the methods provided in the first aspect of the present application.
According to the human body fatigue evaluation optimization method, device, equipment and storage medium, the labor task characterized by low load, multiple gestures and high repeatability is concerned, and the human body fatigue model with subjective and objective combined multiparameter comprehensive evaluation is constructed by comprehensively considering various data and factors, so that the application range is wide, comprehensive, accurate and rapid evaluation of human body fatigue can be realized, and the worker can work in a safe and healthy working environment. Firstly, the invention can match the corresponding optimal evaluation mode according to the specific condition of the acquired data; the comprehensiveness, intelligence and scientificity of the method are improved. And secondly, during fatigue evaluation, the indexes of the gesture, the physiology and the psychology are synthesized, so that the accuracy and the scientificity of the evaluation are improved. Finally, for the physiological index, the invention can correct the target physiological data with important evaluation by utilizing other physiological data, and eliminates the influence of instruments, environments and the like on the acquisition precision of the sensor on the basis of using only a single data source, thereby improving the evaluation precision, reducing the calculation amount and simplifying the evaluation process.
Drawings
FIG. 1 is a flowchart of a first embodiment of a human fatigue evaluation optimization method provided in the present application;
fig. 2 is a schematic diagram of a score calculation flow of the RULA method provided in the present application;
FIG. 3 is a frame diagram of the human fatigue evaluation optimization method provided by the present application;
FIG. 4 is a hardware configuration diagram of a human body fatigue evaluation optimizing device where the human body fatigue evaluation optimizing device is located;
fig. 5 is a schematic structural diagram of a first embodiment of a human fatigue evaluation optimization device provided in the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
The application provides a human body fatigue evaluation optimization method, device, equipment and storage medium, which are used for realizing comprehensive, accurate and rapid evaluation of human body fatigue.
The human body fatigue evaluation optimization method, device, equipment and storage medium collect working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprise two types of data;
splitting the working posture data into sub-working posture data according to the working posture, and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data;
Correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index;
calculating the fatigue of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
the correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
Identifying an error probability for an error feature range based on the correction feature range;
and based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as the target data corresponding to the corrected physiological load index.
Therefore, by focusing on the labor task characterized by low load, multiple postures and high repeatability, various data and factors are comprehensively considered, and a human body fatigue model with subjective and objective combined multiparameter comprehensive evaluation is constructed, the application range is wide, and comprehensive, accurate and rapid evaluation of human body fatigue can be realized, so that workers can work in a safe and healthy working environment. Firstly, the invention can match the corresponding optimal evaluation mode according to the specific condition of the acquired data; the comprehensiveness, intelligence and scientificity of the method are improved. And secondly, during fatigue evaluation, the indexes of the gesture, the physiology and the psychology are synthesized, so that the accuracy and the scientificity of the evaluation are improved. Finally, for the physiological index, the invention can correct the target physiological data with important evaluation by utilizing other physiological data, and eliminates the influence of instruments, environments and the like on the acquisition precision of the sensor on the basis of using only a single data source, thereby improving the evaluation precision, reducing the calculation amount and simplifying the evaluation process.
Specific examples are given below to describe the technical solutions of the present application in detail.
Fig. 1 is a flowchart of a first embodiment of a human fatigue evaluation optimization method provided in the present application. Referring to fig. 1, the method provided in this embodiment may include:
s101, collecting working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprise two types of data.
The human body fatigue evaluation optimization method provided by the embodiment is described by taking the post warehouse-in work as an example.
It should be noted that the working posture data is data formed by recording all working postures in a certain working process through videos and playing back and analyzing all recorded working postures on a computer; the physiological data is recorded by a heart rate band, and the heart rate band is not limited in this embodiment, for example, in one embodiment, the selected heart rate band is a Polar H10 heart rate band. Specifically, polar H10 heart rate area is used for catching heart rate data, and it comprises heart rate sensor and chest area two parts, and the operator wears this heart rate area in the course of the work (experimental process) in the front of the chest, can not influence the normal clear of work. Subjective assessment data is recorded by a paper quality table, specifically, the operator is invited to fill in the paper quality table after the end of the working process.
S102, splitting the working posture data into sub-working posture data according to the working posture, and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; and determining psychological load indexes according to the subjective evaluation data.
The method can determine a specified gesture risk assessment method according to the working gesture data, score the sub-working gesture data according to the specified gesture risk assessment method, and further take the gesture risk average score of all the sub-working gesture data as a gesture load index. The specified gesture risk assessment method is any one of RULA assessment, REBA assessment and OWAS assessment belonging to a table class assessment method, and NIOSH lifting formula assessment belonging to a multiplier class assessment method.
The method for determining the specified gesture risk assessment according to the working gesture data specifically comprises the following steps:
determining important parts of the action according to the working posture data;
based on the concentration degree of the key parts and the type of the concentrated part matching evaluation method;
Determining an action type based on the working gesture data;
and determining a specified gesture risk assessment method according to the action type, wherein the specified gesture risk assessment method belongs to the assessment method type.
Specifically, the selection of the specified pose risk assessment method is determined according to the working pose data, which is not limited in this embodiment. For example, in one embodiment, since the work posture data is relatively more active in the upper limbs during the courier warehouse-in work, the RULA evaluation method is selected as the specified posture risk evaluation method.
Among them, the RULA evaluation method is often used for preventing musculoskeletal diseases in the field of human efficacy evaluation, and the RULA evaluation method uses human posture as a main criterion, and simultaneously considers the condition of force application/load and the condition of muscle use. Specifically, the overall scoring flow is shown in fig. 2.
The method for dividing the working posture data into sub-working posture data according to the working posture at least comprises the following steps:
(1) And determining a representative gesture in the working gesture data, wherein the representative gesture is a high-frequency gesture, and the representative gesture is a completion gesture of a working sub-task, and the working comprises a plurality of sub-tasks.
For example, in one embodiment, during a courier warehouse entry job, the representative gestures in the job gesture data may be a-grab packages, b-lay packages, c-scan packages, d-scan shelf bar codes.
(2) Splitting the work pose data based on the representative pose, wherein the work pose data is used to complete the work and the sub-work pose data is used to complete one of the plurality of sub-tasks.
It should be noted that, the working gesture data is split according to the above-mentioned representative gestures, and each representative gesture includes a plurality of sub-actions, for example: in the process of the warehouse-in work of the express post, the representative gesture a-type grabbing package can comprise four sub-actions a1, a2, a3 and a4, and the description information of the sub-actions represented by a1, a2, a3 and a4 is shown in table 1. And in the sub-working gesture data obtained by splitting, each sub-action gesture data at least corresponds to one sub-action. For example, in one embodiment, in the warehouse-in work of the express post, the working gesture can be split into 16 seed action gestures, which are specifically shown in table 1:
TABLE 1 express post warehouse entry operator actions
After the specified gesture risk assessment method is selected, when the action frequency item score is related, the item score is marked as 0 according to the table type assessment method, and the item score is marked as 1 according to the multiplier type assessment method to operate.
In this embodiment, since the RULA evaluation method is selected and belongs to the table type evaluation method, the action frequency item score is recorded as 0 score for each sub-action score, so as to avoid the influence of repeatedly considering the action frequency.
In specific implementation, counting the occurrence times and total action times of each sub-action and recording RULA score and times of each sub-action; in one embodiment, taking the time of the post warehouse entry as 20 minutes as an example, the action score and the number of times of the operator warehouse entry are recorded, as shown in table 2:
TABLE 2 action score and count for operator L
Preferably, in order to simplify statistics of the number of actions, the present application proposes a method that can study the relation of the action frequency between the work and each sub-action according to the characteristic of high repeatability of the work. The specific simplification process may incorporate the following steps:
(1) The working gestures are divided into a plurality of representative gestures according to the representative gestures in the working gestures.
(2) For each representative gesture, the representative gesture is divided into a plurality of sub-actions (sub-work gestures) according to the operation flow of the work and the operation habit of the operator.
(3) And according to the number of times of occurrence of each representative gesture and the number of sub-action divisions of each representative gesture, obtaining the frequency duty ratio of the sub-actions.
For example, in combination with the contents of table 1, it can be known that all actions in the warehouse entry work of the courier station can be classified into 4 types a, b, c, d (for specific classification information of a, b, c, d, see the above example).
In specific implementation, for example, in this embodiment, 1000 packages are put in the express delivery warehouse in operation.
For the class a action, according to the operation flow of the work, one package needs to be grabbed once, so 1000 class a actions occur in total. The positions of the packages in the basket are randomly distributed, so that the number of packages which are grabbed from the full basket and close to one end (a 1), from the full basket and far from one end (a 2), from the empty basket and close to one end (a 3) and from the empty basket and far from one end (a 4) is approximately equal, the type a actions have 4 sub actions of a 1-a 4, and according to the analysis of the operation flow, the number of times of the 4 sub actions is 1:1:1:1, and therefore, in 1000 types of the actions of the type a, the number of times of the 4 sub actions of a 1-a 4 is 250;
for the b type actions, according to the package distribution situation, the b type actions are divided into 5 sub actions of b 1-b 5 according to the package warehouse-in to 1-5 layers, and when the packages required to be warehouse-in to 1-5 layers respectively have 669, 2804, 3451, 2109 and 967, b1 has 669 times, b2 has 2804 times, b3 has 3451 times, b4 has 2109 times and b5 has 967 times. Wherein the data are obtained from experiments.
For the c-type action, the c-type action can be divided into 3 sub-actions of c 1-c 3 according to the working habit of a tested (operator), different tested have different operation preferences (working habit) through experiments, the frequency of c 1-c 3 is determined by combining the operation preferences of the tested through video analysis, preferably, the operation preferences of the tested are determined through video segments, the frequency ratio of c1, c2 and c3 is obtained, and the frequency of c 1-c 3 is determined according to the frequency ratio and the total frequency of the occurrence of the c-type action.
For the d-type actions, the d-type actions can be divided into 4 sub-actions d 1-d 4 according to the operation flow of the work, and the occurrence times of the sub-actions are calculated according to the operation flow. Specifically, since the adjacent sequentially-put packages placed on the same layer of shelf do not need to repeatedly scan the shelf bar codes, according to the requirements formulated in the experiment, the number of times of the tested scan of the shelf bar codes is about 80% of the number of all packages on the layer, so that the shelf bar codes on the 1 st to 5 th layers need to be scanned 535 times (b1×80%), 2243 times (b2×80%), 2761 times (b3×80%), 1687 (b4×80%) times and 774 (b5×80%) times. Because the shelf bar codes of the fourth layer and the fifth layer are attached to the left side and the right side of the same height, the actions of scanning the shelf bar codes of the fourth layer and the fifth layer are considered to be the same, and the times of scanning can be combined, so d1 has 535 times, d2 has 2243 times, d3 has 2761 times, and d4 has 2461 times. The obtained data is a value obtained by multiplying the number of b-class actions by 80%.
And starting to calculate a gesture load index, specifically, after scoring the sub-work gesture data according to a specified gesture risk assessment method, taking the average score of all the sub-work gesture data as the gesture load index.
Specifically, the average score of all the sub-working posture data is calculated by the following steps:
，
where i represents the ith sub-action type and n represents the total number of sub-action types.
In the present embodiment, the posture load index of the operator can be calculated as 4.183 by combining table 2 and the above formula.
After physiological data is acquired, determining a physiological load index according to the physiological data, calculating a multi-dimensional characteristic of the physiological data according to the physiological load index, wherein the multi-dimensional characteristic at least comprises a time domain, a frequency domain and a nonlinear characteristic, calculating spearman correlation coefficients of each dimensional characteristic in the multi-dimensional characteristic, the gesture load index and the psychological load index respectively, and selecting the dimensional characteristic with the highest spearman correlation coefficient as a target dimension of the physiological load index; wherein the type of the physiological load index is any one of an electrocardio index, an electroencephalogram index, a skin electricity index, a respiration index and a pupil index.
Specifically, in this example, by comparing the electrocardiographic indicators common in three fatigue evaluations: heart Rate (HR), standard deviation of NN interval (Standard Deviation of NN intervals, SDNN) and Low Frequency to High Frequency ratio (Low Frequency/High Frequency, LF/HF) calculate the spearman correlation coefficient. The spearman correlation coefficients for the three electrocardiographic indices are shown in table 3:
TABLE 3 Szelman correlation coefficient calculation
As can be seen from table 3, among the three electrocardiographic indices, the heart rate index has the highest spearman correlation coefficient with the posture load index and the psychological load index, and therefore the heart rate index is selected as the physiological load index.
The Spearman correlation coefficient (Spearman's rank) is a non-parameter index for measuring the dependency of two variables.
In one embodiment, the RR Interval (R-R Interval) time series measured by Polar H10 heart rate belt can be analyzed to obtain heart rate data by using Kubios HRV Standard version. Wherein the RR interval is the time interval between two consecutive R-waves, which is used to analyze the heart's rhythm and variability. For example, in one embodiment, an average heart rate of the operator during a courier warehouse entry operation is measured to be 90 beats/min for 20 minutes.
It should be noted that psychological data may be obtained by NASA-TLX scale, borg fatigue scale, RPE scale, etc.
Preferably, in this embodiment, the physiological data is obtained by selecting the NASA-TLX scale. Wherein the NASA-TLX scale consists of 6 evaluation dimensions, and when the work task is finished, the operator is required to select a number from 0 to 100 in each of the 6 dimensions to represent the degree of the dimension to the load thereof, and the higher the score is, the greater the task load is, the paper pen record is adopted and the experimenter is led into the electronic table.
Specifically, the obtained average score in each dimension is used as a psychological load score. For example, in one embodiment, the operator scores 30, 30, 25, 70, 25, 20 for each dimension, respectively, and then scores 33.333 for psychological burden.
S103, correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index.
The correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
For example, if the physiological load index is selected as the electrocardiograph index, on the basis of acquiring the electrocardiograph index, the electroencephalogram index, and the skin electric index as the physiological data, the electrocardiograph data corresponding to the electrocardiograph index is the target data, and the electroencephalogram data and the skin electric data corresponding to the electroencephalogram index and the skin electric index are the reference data.
Aligning the target data and the reference data based on time domain information of the target data and the reference data;
the target data and the reference data both include time domain features, frequency domain features, and non-linear features, and the target data and the reference data are first aligned based on time information in the time domain features.
Respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
and extracting the characteristics of the aligned data, wherein the target dimension can be one of a time domain, a frequency domain and nonlinearity. If the target dimension is the time domain, extracting time domain features of the aligned target data and reference data; if the target dimension is a frequency domain, extracting frequency domain features of the aligned target data and reference data; and if the target dimension is nonlinear, extracting nonlinear characteristics of the aligned target data and the reference data.
Determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
identifying an error probability for an error feature range based on the correction feature range;
the determining an error feature range based on the feature of the target dimension of the target data, and determining a correction feature range of the feature of the target dimension of the reference data based on time information of the error feature range specifically includes:
determining an identification period based on the period of the jump of adjacent data points in the target data;
and determining the period of the jump of the adjacent data points in the aligned characteristic of the target dimension of the target data, and preferably, if the periods are inconsistent, taking the average period of the jump of the adjacent data points as a period value and taking the period as a recognition period to recognize the data abnormality.
Determining a characteristic range of the data jump abnormality based on the identification period to be used as an error characteristic range; and identifying the transformed features by taking the identification period as a time interval, and finding out a feature range of the data jump abnormality of which the difference value between the lowest value and the highest value of the data is larger than a preset value. If the time domain feature, the feature range is a feature within a time period; if the characteristic is a frequency domain characteristic, the characteristic range is a characteristic in a frequency range; if a nonlinear feature, the feature range is a feature range region.
Determining a correction characteristic range of the reference data aligned with the error characteristic range based on time information of the time domain signal corresponding to the error characteristic range, wherein the time information of the correction characteristic range is aligned with the time information of the error characteristic range;
after determining the error feature range, the time range in the corresponding time domain can be determined according to the range no matter which dimension feature is, and then the correction feature range is determined by utilizing the time range. The method provided by the invention comprises the steps of firstly determining the range of suspected anomalies according to the characteristics in the specific dimension, and then finding the range of the reference data with the same time information by utilizing the characteristics of time domain alignment, so as to find the characteristics of the reference data corresponding to the range. The method and the device have the advantages that data fusion and complex calculation are not needed, the time domain information is used as a bridge for the features in all dimensions in a time alignment mode, and the reference features corresponding to the time domain information are found, so that correction is performed, the accuracy of single-signal fatigue identification is improved, and meanwhile, the calculation amount is reduced.
The error probability of the error feature range is identified based on the correction feature range, specifically including:
and calculating error probability based on the characteristic jump degree of the characteristic of the correction characteristic range and the characteristic jump degree of the error characteristic range.
Preferably, the error probability can be calculated by using a characteristic jump degree ratio, wherein the characteristic jump degree is the difference between the highest value of the characteristic and the lowest value of the characteristic.
And based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as the target data corresponding to the corrected physiological load index.
Compared with the method for evaluating the fatigue state by using a single index in the prior art, the method provided by the invention can uniformly evaluate the fatigue state by using a plurality of indexes, and improves the accuracy of the fatigue state. When the physiological load index is evaluated, compared with the prior art that only one-dimensional data is used for evaluation or multiple-dimensional data are used for evaluation, on one hand, the data of one dimension are still used as main sources of evaluation, so that the calculation processes of data fusion and result fusion are reduced, the overall calculation amount and calculation time are reduced, and the evaluation efficiency is improved; on the other hand, the corresponding range under each feature is found by using the aligned information, and finally, the data with the same range and different dimensions are used for correction, so that the accuracy of the data with the single dimension is improved, and the accuracy of evaluation is further improved. Therefore, the accuracy is improved, the calculated amount is reduced, the evaluation process is simplified, and the evaluation efficiency is improved.
S104, calculating the fatigue degree of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index.
Preferably, the weights of the posture load index, the physiological load index and the psychological load index can be determined by a weighting method based on an index difference in an objective weighting method.
Specifically, the weighting coefficient is determined by a weighting method based on index difference in an objective weighting method and by a mean square error method: taking the j-th evaluation index x j The mean square error of each observation value is normalized and then used as a corresponding weight coefficient, please refer to the following formula:
，
wherein the method comprises the steps of，/>J represents the number of items of the evaluation index, m represents the total number of items of the evaluation index,/and%>Weight coefficient indicating the j-th evaluation index, < ->The standard deviation of the j-th evaluation index is represented, n represents the number of terms of the observed value, and x ij Observation value indicating the j-th evaluation index in the i-th sample, < >>Represents the average value of the j-th evaluation index,kfor cyclic variables, ++ >Represent the firstkStandard deviation of item evaluation index.
In the present embodiment, three weight coefficients, namely, gesture load index, are involved in totalWeight of +.>Index of physiological load->Weight of +.>And psychological stress index->Weight of +.>。
For example, in one embodiment, the collected work posture data, physiological data, and subjective assessment data of ten operators are calculated，/>，/>。
The method for calculating the fatigue degree of the human body specifically comprises the following steps:
，
wherein HFL represents human fatigue;a gesture load index; />Representing a physiological load index; />Representing psychological load index; />、/>、/>Are all evaluation index constants; />A weight indicating a gesture load index; />A weight representing a physiological load index; />And (5) representing the weight of the psychological load index.
In one embodiment of the present invention, in one embodiment,is that the gesture load index score is at risk and risk freeBoundary value, taking 3.000;indicating the baseline physiological load index in the resting state, the average heart rate of the operator in the resting state is measured to be 60 times/min, 60>The mental load index score is 50.000 when the task is neither simple nor complex, and the human body fatigue degree of the operator is 1.026 by combining the posture load index, the physiological load index and the mental load index of the operator in the above example.
After the human body fatigue degree is calculated, the human body fatigue degree and the fatigue degree grade are obtained; wherein the fatigue level is fatigue if the human body fatigue is greater than a specified value; and if the human body fatigue degree is smaller than a specified value, the fatigue degree grade is not tired.
Specifically, the specified value is set according to actual needs, and is not limited in this embodiment, for example, the specified value is 1.000 in one embodiment. Then whenWhen the task is represented, the operator is easy to fatigue, and the larger the numerical value is, the more easily the operator is tired; when->When this task is represented, it is not easy to cause fatigue of the operator, and the smaller the numerical value is, the less easy to cause fatigue.
It should be noted that, after the fatigue degree and the fatigue degree level of the human body are obtained, if the fatigue level is fatigue, an operation improvement scheme is determined according to the fatigue level and the operation.
Specifically, please refer to fig. 3 for a frame diagram of the human fatigue evaluation optimization method provided in the present application.
According to the human body fatigue evaluation optimization method, labor tasks characterized by low load, multiple postures and high repeatability are concerned, and a human body fatigue model with multiple comprehensive evaluation of multiple parameters combined by subjects and objects is constructed by comprehensively considering multiple data and factors, so that the application range is wide, comprehensive, accurate and rapid evaluation of human body fatigue can be realized, and workers can work in safe and healthy working environments. Specifically, the invention considers both the working posture and physiology and psychological load, synthesizes subjective and objective factors, and improves the evaluation accuracy; when each factor is calculated, different evaluation methods and evaluation dimensions are provided according to different work types, for the work gestures, the representative gestures are determined according to specific works, so that each sub-action is divided, for physiological load indexes, multiple types such as electrocardio and electroencephalogram are provided, each type is provided with multiple dimensions for selection, on one hand, the universality of the evaluation method is improved, namely, the evaluation of any work can be completed, on the other hand, the evaluation method most suitable for each evaluation object is selected, and the evaluation accuracy is improved.
Corresponding to the embodiment of the human body fatigue evaluation optimization method, the application also provides an embodiment of the human body fatigue evaluation optimization device.
The embodiment of the human body fatigue evaluation optimizing device can be applied to human body fatigue evaluation optimizing equipment. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory through a processor of human body fatigue evaluation optimizing equipment where the device is located. From the hardware level, as shown in fig. 4, a hardware structure diagram of the human body fatigue evaluation optimizing device where the human body fatigue evaluation optimizing device is located in the embodiment is shown in fig. 4, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 4, where the human body fatigue evaluation optimizing device where the device is located generally includes other hardware according to the actual function of the human body fatigue evaluation optimizing device, which is not described herein again.
Fig. 5 is a schematic structural diagram of a first embodiment of a human fatigue evaluation optimization device provided in the present application, please refer to fig. 5, and the device provided in the present embodiment may include an acquisition module 510, a processing module 520 and a calculation module 530, wherein,
The acquisition module 510 is configured to acquire working posture data, physiological data, and subjective evaluation data;
the processing module 520 is configured to split the working posture data into sub-working posture data according to a working posture, and calculate a posture load index according to the sub-working posture data; acquiring time domain, frequency domain and nonlinear characteristics in the physiological data, and determining a physiological load index; determining psychological load indexes according to the subjective evaluation data;
the calculating module 530 is configured to correct target data corresponding to the physiological load index according to reference data corresponding to the physiological load index;
the calculation module is further used for calculating the fatigue degree of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
the correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
Aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
identifying an error probability for an error feature range based on the correction feature range;
and based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as the target data corresponding to the corrected physiological load index.
The apparatus provided in this embodiment may be used to perform the steps of the method shown in fig. 1, and the implementation principle and implementation procedure are similar to those described above, and are not repeated here.
With continued reference to fig. 4, the present application further provides a human fatigue evaluation optimization device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of any one of the methods provided in the first aspect of the present application when the processor executes the program.
The present application also provides a storage medium having stored thereon a program which when executed by a processor performs the steps of any of the methods provided in the first aspect of the present application.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.

Claims (8)

1. A method for optimizing human fatigue assessment, the method comprising:
collecting working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprise two types of data;
splitting the working posture data into sub-working posture data according to the working posture, and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data;
correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index;
calculating the fatigue of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
the correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
Determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
identifying an error probability for an error feature range based on the correction feature range;
based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as target data corresponding to the corrected physiological load index;
the method for determining the physiological load index according to the work comprises the steps of obtaining the time domain, the frequency domain and the nonlinear characteristics of the physiological load index, and determining the target dimension of the physiological load index, wherein the method specifically comprises the following steps:
Determining a physiological load index according to the physiological data, calculating a multi-dimensional characteristic of the physiological data according to the physiological load index, wherein the multi-dimensional characteristic at least comprises a time domain, a frequency domain and a nonlinear characteristic, respectively calculating spearman correlation coefficients of each dimensional characteristic in the multi-dimensional characteristic, the posture load index and the psychological load index, and selecting the dimensional characteristic with the highest spearman correlation coefficient as a target dimension of the physiological load index; wherein the physiological load index is any one of an electrocardio index, an electroencephalogram index, a skin electricity index, a respiration index and a pupil index;
the determining an error feature range based on the feature of the target dimension of the target data, and determining a correction feature range of the feature of the target dimension of the reference data based on time information of the error feature range specifically includes:
determining an identification period based on the period of the jump of adjacent data points in the target data;
determining a characteristic range of the data jump abnormality based on the identification period to be used as an error characteristic range;
determining a correction characteristic range of the reference data aligned with the error characteristic range based on time information of the time domain signal corresponding to the error characteristic range, wherein the time information of the correction characteristic range is aligned with the time information of the error characteristic range;
The error probability of the error feature range is identified based on the correction feature range, specifically including:
and calculating error probability based on the characteristic jump degree of the characteristic of the correction characteristic range and the characteristic jump degree of the error characteristic range.
2. The method of claim 1, wherein the splitting the working pose data into sub-working pose data according to working pose comprises at least:
determining a representative gesture in the work gesture data, the representative gesture being a high frequency gesture and the representative gesture being a completion gesture of a work sub-task, wherein a work includes a plurality of sub-tasks;
and splitting the work posture data based on the representative posture, wherein the work posture data is used for completing the work and the sub-work posture data is used for completing one of the plurality of sub-tasks.
3. The method according to claim 2, wherein a specified pose risk assessment method is determined according to the work pose data and the sub-work pose data is scored according to the specified pose risk assessment method, and further a pose risk average score of all the sub-work pose data is used as the pose load index; the specified gesture risk assessment method is any one of RULA assessment, REBA assessment and OWAS assessment belonging to a table class assessment method and NIOSH lifting formula assessment method belonging to a multiplier class assessment method;
The method for determining the specified gesture risk assessment according to the working gesture data specifically comprises the following steps:
determining important parts of actions according to the working posture data;
based on the concentration degree of the key parts and the type of the concentrated part matching evaluation method;
determining an action type based on the work posture data;
and determining a specified gesture risk assessment method according to the action type, wherein the specified gesture risk assessment method belongs to the assessment method type.
4. A method according to claim 3, wherein each of the sub-job gesture data corresponds to a sub-action, and the average score of the job gesture data is calculated by:
,
where i represents the ith sub-action type and n represents the total number of sub-action types.
5. The method according to claim 1, wherein the calculating of the degree of fatigue of the human body comprises:
,
wherein HFL represents human fatigue;a gesture load index; />Representing a physiological load index; />Representing psychological load index; />、/>、/>Are all evaluation index constants; />A weight indicating a gesture load index; />A weight representing a physiological load index; />And (5) representing the weight of the psychological load index.
6. A human body fatigue evaluation optimizing device is characterized by comprising an acquisition module, a processing module and a calculation module, wherein,
the acquisition module is used for acquiring working posture data, physiological data and subjective evaluation data, wherein the physiological data at least comprises two types of data;
the processing module is used for splitting the working posture data into sub-working posture data according to the working posture and calculating a posture load index according to the sub-working posture data; determining a physiological load index according to work, acquiring time domain, frequency domain and nonlinear characteristics of the physiological load index, and determining a target dimension of the physiological load index; determining psychological load indexes according to the subjective evaluation data;
the calculation module is used for correcting target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index;
the calculation module is further used for calculating the fatigue degree of the human body according to the posture load index, the target dimension of the physiological load index, the psychological load index, the weight of the posture load index, the weight of the physiological load index, the weight of the psychological load index and the target data corresponding to the corrected physiological load index;
The correcting the target data corresponding to the physiological load index according to the reference data corresponding to the physiological load index specifically includes:
determining target data corresponding to the physiological load index and reference data of the target data, wherein the reference data is physiological data except the target data in the physiological data, and the types of the reference data and the target data are different;
aligning the target data and the reference data based on time domain information of the target data and the reference data;
respectively extracting the characteristics of the corresponding target dimensions of the aligned target data and the reference data;
determining an error feature range based on the features of the target dimension of the target data, and determining a correction feature range of the features of the target dimension of the reference data based on time information of the error feature range;
identifying an error probability for an error feature range based on the correction feature range;
based on the characteristics of the target dimension of the target data in the error probability correction error characteristic range, obtaining the corrected characteristics of the target dimension of the target data as target data corresponding to the corrected physiological load index;
The method for determining the physiological load index according to the work comprises the steps of obtaining the time domain, the frequency domain and the nonlinear characteristics of the physiological load index, and determining the target dimension of the physiological load index, wherein the method specifically comprises the following steps:
determining a physiological load index according to the physiological data, calculating a multi-dimensional characteristic of the physiological data according to the physiological load index, wherein the multi-dimensional characteristic at least comprises a time domain, a frequency domain and a nonlinear characteristic, respectively calculating spearman correlation coefficients of each dimensional characteristic in the multi-dimensional characteristic, the posture load index and the psychological load index, and selecting the dimensional characteristic with the highest spearman correlation coefficient as a target dimension of the physiological load index; wherein the physiological load index is any one of an electrocardio index, an electroencephalogram index, a skin electricity index, a respiration index and a pupil index;
the determining an error feature range based on the feature of the target dimension of the target data, and determining a correction feature range of the feature of the target dimension of the reference data based on time information of the error feature range specifically includes:
determining an identification period based on the period of the jump of adjacent data points in the target data;
Determining a characteristic range of the data jump abnormality based on the identification period to be used as an error characteristic range;
determining a correction characteristic range of the reference data aligned with the error characteristic range based on time information of the time domain signal corresponding to the error characteristic range, wherein the time information of the correction characteristic range is aligned with the time information of the error characteristic range;
the error probability of the error feature range is identified based on the correction feature range, specifically including:
and calculating error probability based on the characteristic jump degree of the characteristic of the correction characteristic range and the characteristic jump degree of the error characteristic range.
7. A human fatigue assessment optimizing device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method according to any of claims 1-5 when the program is executed.
8. A storage medium having a program stored thereon, which when executed by a processor, implements the steps of the method of any of claims 1-5.
CN202410077649.7A 2024-01-19 2024-01-19 Human body fatigue evaluation optimization method, device, equipment and storage medium Active CN117594242B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410077649.7A CN117594242B (en) 2024-01-19 2024-01-19 Human body fatigue evaluation optimization method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410077649.7A CN117594242B (en) 2024-01-19 2024-01-19 Human body fatigue evaluation optimization method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN117594242A CN117594242A (en) 2024-02-23
CN117594242B true CN117594242B (en) 2024-04-09

Family

ID=89913741

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410077649.7A Active CN117594242B (en) 2024-01-19 2024-01-19 Human body fatigue evaluation optimization method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117594242B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6616104B1 (en) * 2002-06-24 2003-09-09 Lockheed Martin Corporation Spacecraft configuration and attitude steering method for highly inclined orbit (HIO) communications
CN101690666A (en) * 2009-10-13 2010-04-07 北京工业大学 Driving working load calculation method of automobile driver
CN104825174A (en) * 2015-04-17 2015-08-12 深圳市元征科技股份有限公司 Fatigue state detection method and terminal
JP2019192160A (en) * 2018-04-27 2019-10-31 日本電信電話株式会社 Optimization device, optimization method, and program
CN114595921A (en) * 2021-12-30 2022-06-07 中国民航管理干部学院 Comprehensive evaluation system and method for pilot fatigue of helicopter in marine operation
CN114678039A (en) * 2022-04-13 2022-06-28 厦门大学 Singing evaluation method based on deep learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6616104B1 (en) * 2002-06-24 2003-09-09 Lockheed Martin Corporation Spacecraft configuration and attitude steering method for highly inclined orbit (HIO) communications
CN101690666A (en) * 2009-10-13 2010-04-07 北京工业大学 Driving working load calculation method of automobile driver
CN104825174A (en) * 2015-04-17 2015-08-12 深圳市元征科技股份有限公司 Fatigue state detection method and terminal
JP2019192160A (en) * 2018-04-27 2019-10-31 日本電信電話株式会社 Optimization device, optimization method, and program
CN114595921A (en) * 2021-12-30 2022-06-07 中国民航管理干部学院 Comprehensive evaluation system and method for pilot fatigue of helicopter in marine operation
CN114678039A (en) * 2022-04-13 2022-06-28 厦门大学 Singing evaluation method based on deep learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
狭小工作舱上肢作业姿势疲劳特性评估;范文;余隋怀;王文军;徐剑波;;机械科学与技术;20150515(第05期);668-673页 *

Also Published As

Publication number Publication date
CN117594242A (en) 2024-02-23

Similar Documents

Publication Publication Date Title
EP3617815B1 (en) Work support device, work support method, and work support program
US11350868B2 (en) Electrocardiogram information processing method and electrocardiogram workstation system
EP3692903A1 (en) Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus
JP2022523741A (en) ECG processing system for depiction and classification
US11783924B2 (en) ECG information processing method and ECG workstation
Johnson et al. Patient specific predictions in the intensive care unit using a Bayesian ensemble
Gupta et al. PCA as an effective tool for the detection of R-peaks in an ECG signal processing
CN102908130A (en) Residual-based monitoring of human health
CN116602642B (en) Heart rate monitoring method, device and equipment
TWI469764B (en) System, method, recording medium and computer program product for calculating physiological index
CN111680913B (en) Overload work detection method and system for warmen
CN105611872A (en) An apparatus and method for evaluating multichannel ECG signals
Melgarejo-Meseguer et al. On the beat detection performance in long-term ECG monitoring scenarios
JP3054708B1 (en) Stress measurement device
CN117594242B (en) Human body fatigue evaluation optimization method, device, equipment and storage medium
CN113128585B (en) Deep neural network based multi-size convolution kernel method for realizing electrocardiographic abnormality detection and classification
Kheiri et al. Human reliability modeling in occupational environments toward a safe and productive operator 4.0
Speroff et al. Lens Model Analysis of Hemodynamic status in the critically III
CN114469022A (en) Method and device for reviewing alarm event and readable storage medium
CN104834702B (en) For the subject selection method of science research programs
Shebanin et al. Canonical mathematical model and information technology for cardio-vascular diseases diagnostics
CN115553777A (en) Non-contact mental stress detection method and system
Mistry et al. Efficient prediction of heart disease using cross machine learning techniques
Casañez-Ventura et al. QRS delineation algorithms comparison and model fine tuning for automatic clinical classification
CN111666272A (en) Method and device for establishing sewing product working hour standard and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant