CN116596320B - Risk assessment method and system for coal mine operators - Google Patents

Risk assessment method and system for coal mine operators Download PDF

Info

Publication number
CN116596320B
CN116596320B CN202310835476.6A CN202310835476A CN116596320B CN 116596320 B CN116596320 B CN 116596320B CN 202310835476 A CN202310835476 A CN 202310835476A CN 116596320 B CN116596320 B CN 116596320B
Authority
CN
China
Prior art keywords
risk
coal mine
evaluation value
value
behavior
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
CN202310835476.6A
Other languages
Chinese (zh)
Other versions
CN116596320A (en
Inventor
周亚东
周应江
闫建华
王云泉
薛泽宇
赵学江
杨轲
赵玉宝
郭超荣
陈洪林
杜大文
葛庆岗
何华刚
史劢
刘波
杜祎康
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.)
Beijing Zhonggang'an Technology Co ltd
China National Coal Group Corp
China University of Geosciences
China University of Mining and Technology Beijing CUMTB
Peking University Third Hospital Peking University Third Clinical Medical College
Original Assignee
Beijing Zhonggang'an Technology Co ltd
China National Coal Group Corp
China University of Geosciences
China University of Mining and Technology Beijing CUMTB
Peking University Third Hospital Peking University Third Clinical Medical College
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 Beijing Zhonggang'an Technology Co ltd, China National Coal Group Corp, China University of Geosciences, China University of Mining and Technology Beijing CUMTB, Peking University Third Hospital Peking University Third Clinical Medical College filed Critical Beijing Zhonggang'an Technology Co ltd
Priority to CN202310835476.6A priority Critical patent/CN116596320B/en
Publication of CN116596320A publication Critical patent/CN116596320A/en
Application granted granted Critical
Publication of CN116596320B publication Critical patent/CN116596320B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • 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
    • 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

Abstract

The invention provides a risk assessment method and a risk assessment system for coal mine operators, wherein the risk assessment method and the risk assessment system are characterized in that the physiological parameters and the psychological parameters of the coal mine operators to be assessed are obtained, the mapping relation and the weight between the physiological parameters and the psychological parameters are determined, the human factor risk characteristic information is extracted from a history file, the human factor risk characteristic information, the mapping relation and the weight are input into a human factor accident risk assessment model to carry out risk assessment, the risk assessment value of the coal mine operators to be assessed is obtained, the risk assessment value is used for carrying out rating, and a risk assessment report containing the risk grade of the coal mine operators to be assessed is generated and output. According to the scheme, the risk assessment is carried out by utilizing the artificial accident risk assessment model based on the mapping relation between the psychological parameters and the physiological parameters of the coal mine operators to be assessed and the historical artificial risk characteristic information, so that the aim of rapidly and objectively assessing the coal mine operators is fulfilled, and the requirements of rapid screening of a plurality of coal mine operators are met.

Description

Risk assessment method and system for coal mine operators
Technical Field
The invention relates to the technical field of big data, in particular to a risk assessment method and a risk assessment system for coal mine operators.
Background
Coal mine operation comprises extremely complex processes, has a plurality of dangerous sources, is easy to generate safety problems, and reaches conclusion after the American famous safety engineer is studied by Hairy: the concept that the majority of safety accidents are caused by unsafe behaviors of people is common to people because safety management must be based on people.
Therefore, before the staff working in the coal mine works on duty, the staff needs to combine the related physical and mental health states, and whether the staff can carry out safe production is judged from the perspective of the staff.
However, the existing artificial risk assessment method is strong in subjectivity and long in assessment period, and cannot meet the rapid screening requirements of numerous coal mine operators.
Disclosure of Invention
Therefore, the embodiment of the invention provides a risk assessment method and a risk assessment system for coal mine operators, so as to objectively and rapidly carry out risk assessment on the coal mine operators and fulfill the aim of rapidly screening the plurality of coal mine operators.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
the first aspect of the embodiment of the invention discloses a risk assessment method for coal mine operators, which comprises the following steps:
Acquiring identity information and post information of coal mine operators to be evaluated;
performing physiological and psychological health detection on the coal mine worker to be evaluated to obtain physiological parameters and psychological parameters;
respectively acquiring historical accident risk characteristic information, historical post risk characteristic information and historical environment risk characteristic information corresponding to the post information from a historical accident report, historical post information and historical expert post analysis opinion;
extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information;
determining the mapping relation between the physiological parameters and the psychological parameters and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation;
inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk assessment model for risk assessment to obtain a risk assessment value of the coal mine worker to be assessed;
ranking the risk level of the coal mine worker to be evaluated based on the risk evaluation value;
generating and outputting a risk assessment report containing the identity information, the post information and the risk level for the coal mine worker to be assessed;
The risk assessment process of the human factor accident risk assessment model comprises the following steps:
according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value;
searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic;
if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value;
determining the crowd category of the coal mine worker to be evaluated as the crowd category corresponding to the health evaluation value;
searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node;
and coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value.
Preferably, the detecting the physiological and psychological health of the coal mine operator to be evaluated to obtain the physiological parameter and psychological parameter includes:
performing physiological health detection on the coal mine operators to be evaluated by using a rapid pre-post health screening system to obtain various physiological parameters of the coal mine operators to be evaluated;
And acquiring questionnaire investigation information filled by the coal mine operators to be evaluated, and performing psychological analysis to obtain all psychological parameters of the coal mine operators to be evaluated.
Preferably, extracting the human factor risk feature information from the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information includes:
and inputting the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information into a man-machine-ring interaction model for feature analysis, and extracting human factor risk feature information representing the accident caused by human factors.
Preferably, the construction process of the human factor accident risk assessment model comprises the following steps:
constructing a behavior evaluation submodel containing a mapping relation between risk behavior characteristics and health evaluation values;
assigning a preset risk value corresponding to the risk behavior characteristic in the evaluation sub-model;
constructing a crowd evaluation submodel comprising a knowledge graph and a corresponding relation between crowd categories and health evaluation values; the knowledge graph comprises the association relation between crowd category nodes and risk nodes and the association relation between the risk nodes and crowd risk assessment values;
Constructing a human factor accident risk assessment model comprising the behavior assessment sub-model and the crowd assessment sub-model;
the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators are input into the human factor accident risk assessment model;
according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value;
searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic;
if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value;
determining the crowd category of the coal mine operator as the crowd category corresponding to the health evaluation value;
searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node;
coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value;
Judging whether the risk evaluation value is accurate or not;
if the risk assessment value is accurate, obtaining a trained artificial accident risk assessment model;
if the risk assessment value is inaccurate, continuing to input the mapping relation between the physiological parameter and the psychological parameter of the next coal mine worker and the artificial risk characteristic information corresponding to the post information into the artificial accident risk assessment model for training until the output risk assessment value and the risk information are accurate.
Preferably, the determining whether the risk assessment value is accurate includes:
acquiring a risk assessment value of an expert based on a mapping relation between physiological parameters and psychological parameters of coal mine operators and human factor risk characteristic information corresponding to post information, and obtaining the risk assessment value of manual assessment;
if the difference value between the risk evaluation value and the artificial risk evaluation value is within a preset range, determining that the risk evaluation value is accurate;
and if the difference value between the risk evaluation value and the artificial risk evaluation value is not in the preset range, determining that the risk evaluation value is inaccurate.
Preferably, the grading the risk level of the coal mine worker to be evaluated based on the risk evaluation value includes:
If the risk assessment value is smaller than or equal to a preset value, determining that the risk level of the coal mine operator to be assessed is low risk;
if the risk assessment value exceeds within 10% of a preset value, determining that the risk level of the coal mine operator to be assessed is a medium risk;
and if the risk assessment value exceeds more than 10% of a preset value, determining that the risk level of the coal mine operator to be assessed is high risk.
The second aspect of the embodiment of the invention discloses a risk assessment system for coal mine operators, which comprises the following components:
the acquisition unit is used for acquiring identity information and post information of coal mine operators to be evaluated; respectively acquiring historical accident risk characteristic information, historical post risk characteristic information and historical environment risk characteristic information corresponding to the post information from a historical accident report, historical post information and historical expert post analysis opinion;
the health detection unit is used for detecting the physiological and psychological health of the coal mine operators to be evaluated to obtain physiological parameters and psychological parameters;
the extraction unit is used for extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information;
The determining unit is used for determining the mapping relation between the physiological parameter and the psychological parameter and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation;
the evaluation unit is used for inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk evaluation model to perform risk evaluation, so as to obtain a risk evaluation value of the coal mine worker to be evaluated; the risk assessment process of the human factor accident risk assessment model comprises the following steps: according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value; searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic; if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value; determining the crowd category of the coal mine worker to be evaluated as the crowd category corresponding to the health evaluation value; searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node; coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value;
The grading unit is used for grading the risk grade of the coal mine worker to be evaluated based on the risk evaluation value;
the generation unit is used for generating and outputting a risk assessment report containing the identity information, the post information and the risk level for the coal mine worker to be assessed.
Preferably, the health detection unit includes:
the physiological detection subunit is used for detecting physiological health of the coal mine operators to be evaluated by utilizing a rapid pre-post health screening system to obtain various physiological parameters of the coal mine operators to be evaluated;
and the psychological detection subunit is used for acquiring the questionnaire information filled in by the coal mine operators to be evaluated, and carrying out psychological analysis to obtain all psychological parameters of the coal mine operators to be evaluated.
Preferably, the extraction unit is specifically configured to:
and inputting the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information into a man-machine-ring interaction model for feature analysis, and extracting human factor risk feature information representing the accident caused by human factors.
Preferably, the method further comprises:
The construction unit is used for constructing a behavior evaluation submodel containing a mapping relation between risk behavior characteristics and health evaluation values; assigning a preset risk value corresponding to the risk behavior characteristic in the evaluation sub-model; constructing a crowd evaluation submodel comprising a knowledge graph and a corresponding relation between crowd categories and health evaluation values; the knowledge graph comprises the association relation between crowd category nodes and risk nodes and the association relation between the risk nodes and crowd risk assessment values; constructing a human factor accident risk assessment model comprising the behavior assessment sub-model and the crowd assessment sub-model;
the training unit is used for inputting the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators into the human factor accident risk assessment model; according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value; searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic; if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value; determining the crowd category of the coal mine operator as the crowd category corresponding to the health evaluation value; searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node; coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value; judging whether the risk evaluation value is accurate or not; if the risk assessment value is accurate, obtaining a trained artificial accident risk assessment model; if the risk assessment value is inaccurate, continuing to input the mapping relation between the physiological parameter and the psychological parameter of the next coal mine worker and the artificial risk characteristic information corresponding to the post information into the artificial accident risk assessment model for training until the output risk assessment value and the risk information are accurate.
Based on the risk assessment method and system for the coal mine operators provided by the embodiment of the invention, the identity information and the post information of the coal mine operators to be assessed are obtained; performing physiological and psychological health detection on the coal mine worker to be evaluated to obtain physiological parameters and psychological parameters; respectively acquiring historical accident risk characteristic information, historical post risk characteristic information and historical environment risk characteristic information corresponding to the post information from a historical accident report, historical post information and historical expert post analysis opinion; extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information; determining the mapping relation between the physiological parameters and the psychological parameters and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation; inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk assessment model for risk assessment to obtain a risk assessment value of the coal mine worker to be assessed; ranking the risk level of the coal mine worker to be evaluated based on the risk evaluation value; generating and outputting a risk assessment report containing the identity information, the post information and the risk level for the coal mine worker to be assessed; the risk assessment process of the human factor accident risk assessment model comprises the following steps: according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value; searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic; if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value; determining the crowd category of the coal mine worker to be evaluated as the crowd category corresponding to the health evaluation value; searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node; and coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value. According to the scheme, the risk assessment is carried out by utilizing the artificial accident risk assessment model based on the mapping relation between the psychological parameters and the physiological parameters of the coal mine operators to be assessed and the historical artificial risk characteristic information, so that the aim of rapidly and objectively assessing the coal mine operators is fulfilled, and the requirements of rapid screening of a plurality of coal mine operators are met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a technical roadmap of a risk assessment system for coal mine operators according to an embodiment of the present invention;
FIG. 2 is a flow chart of a risk assessment method for coal mine operators according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for constructing a model for risk assessment of human-caused accidents according to an embodiment of the present invention;
fig. 4 is a diagram of a risk assessment system for coal mine operators according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the present disclosure, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The background technology shows that the existing artificial risk assessment method is strong in subjectivity and long in assessment period, and cannot meet the rapid screening requirements of a plurality of coal mine operators.
Therefore, the embodiment of the application discloses a risk assessment method and a risk assessment system for coal mine operators, in the scheme, the risk assessment is carried out by utilizing a human factor accident risk assessment model based on the mapping relation between psychological parameters and physiological parameters of the coal mine operators to be assessed and historical human factor risk characteristic information, so that the aim of rapidly and objectively assessing the coal mine operators is fulfilled, and the requirements of rapid screening of a plurality of coal mine operators are met.
Fig. 1 is a technical roadmap of a risk assessment system for coal mine operators according to an embodiment of the present invention.
The psychological parameters and the physiological parameters of coal mine operators to be evaluated are obtained through an intelligent physical and mental health examination, a rapid pre-post health screening system, a pre-post balance rapid screening and a human factor risk monitoring technology, and the mapping relation and the weight between the psychological parameters and the physiological parameters are determined through a pre-built mapping relation model.
It should be noted that the means for obtaining the psychological parameter and the physiological parameter are not limited to the above-mentioned embodiments of the present invention.
The historical accident report, the historical post data and the historical expert post analysis opinion are obtained through the accident report collection and arrangement, the literature data collection and arrangement and the expert post human factor risk analysis, the human-machine-loop interaction model is utilized to conduct human factor analysis on the historical accident report, the historical post data and the historical expert post analysis opinion, and corresponding human factor risk characteristic information representing accidents caused by human factors is extracted according to the post information of coal mine operators to be evaluated.
And inputting the mapping relation, the weight and the human factor risk characteristic information into a human factor accident risk assessment model to perform behavior risk assessment and crowd risk assessment, and performing coupling analysis on the behavior risk assessment value and the crowd risk assessment value to obtain a risk assessment value of coal mine operators to be assessed.
The human factor accident risk assessment model is composed of an operator behavior model and an artificial intelligence assessment model.
The worker behavior model is used for carrying out risk assessment on the behaviors of workers based on the relation between the behaviors of the workers in the coal mine and human factor factors, and obtaining a behavior risk assessment value.
The artificial intelligent evaluation model is used for dividing the types of people of coal mine operators to be evaluated based on a pre-constructed knowledge graph, and obtaining crowd risk evaluation values corresponding to the types of people.
The knowledge graph is obtained by dividing a plurality of sample coal mine operators based on crowd risks and constructing nodes based on the divided crowd types, risk factors and risk values by utilizing an artificial risk graph neural network model.
After the artificial accident risk assessment model is constructed, the artificial accident risk assessment model is tested, which comprises the following steps: and (3) carrying out on-site monitoring data analysis on the psychological parameters and the physiological parameters of the coal mine operators to be evaluated, which are obtained by an expert, so as to obtain a risk evaluation value for manual evaluation, comparing the risk evaluation value for manual evaluation with a risk evaluation value output by a human factor accident risk evaluation model, and if the difference value is within a preset range, then the human factor accident risk evaluation model is proved to be in accordance with the requirements.
Based on the technical roadmap of the risk assessment system for coal mine operators disclosed in the embodiment of the present invention, correspondingly, as shown in fig. 2, a flowchart of a risk assessment method for coal mine operators disclosed in the embodiment of the present invention is provided, and the method includes the following steps:
step S201: and acquiring identity information and post information of coal mine operators to be evaluated.
In step S201, the identity information includes name, gender, identification card number, etc., and the post information includes: post, working time, working place, etc.
Step S202: and carrying out physiological and psychological health detection on the coal mine worker to be evaluated to obtain physiological parameters and psychological parameters.
In step S202, the physiological parameters include: heart rate variability index, heart rate, pulse, respiration rate, blood oxygen, blood pressure, etc.
Psychological parameters include: anxiety parameters, depression parameters, personality parameters, emotion parameters, mood parameters, and the like.
In the specific implementation process of step S202, physiological parameters of coal mine operators to be evaluated are detected and obtained by using an intelligent physical and mental health inspection, a rapid pre-post health screening system, a pre-post balance fast screening and a human factor risk monitoring technology, questionnaire survey information filled by the coal mine operators to be evaluated is obtained, and psychological analysis is performed to obtain all psychological parameters of the coal mine operators to be evaluated.
It should be noted that, the embodiment of the present invention is not limited to specific psychological analysis means, and the existing technical means may be adopted.
Step S203: and respectively acquiring the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information corresponding to the post information from the historical accident report, the historical post information and the historical expert post analysis opinion.
In step S203, the historical accident risk feature information is used to characterize a human risk feature that caused the accident to occur, for example, a worker fatigue operation.
The historical post risk feature information is used to characterize the human factor risk features under post-specific conditions, e.g., posts working aloft are not wearing safety belts.
The historical environmental risk profile information is used to characterize the artificial risk profile under environmental specific conditions, e.g., without a gas mask in a toxic environment.
Step S204: and extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information.
In the specific implementation process of step S204, the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information are input into a man-machine-ring interaction model to perform feature analysis, and the human factor risk feature information representing the accident caused by human factors is extracted.
The following are several examples of the personal risk profile information provided by the present embodiment, for example: no safety helmet, violating operation flow, insufficient rest time, and the like.
The embodiment of the invention is not limited, and the effect of extracting the human factor risk characteristic information representing the accident caused by human factors can be achieved by adopting the existing human-machine-ring interaction model.
Step S205: and determining the mapping relation between the physiological parameter and the psychological parameter and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation.
In step S205, the mapping relationship between the physiological parameter and the psychological parameter, for example, the heart rate-anxiety parameter, is one set of mapping relationships, and the respiration rate-anxiety parameter is another set of mapping relationships.
The weight corresponding to the mapping relation characterizes the degree of tightness of the relation between the physiological parameter and the psychological parameter, for example, the weight corresponding to the heart rate-anxiety parameter is 5, the weight corresponding to the respiration rate-anxiety parameter is 6, and the degree of tightness of the relation between the heart rate-anxiety parameter is smaller than that of the respiration rate-anxiety parameter.
In the specific implementation process of step S205, the obtained physiological parameters and psychological parameters of the coal mine operator to be evaluated are input into a pre-constructed physiological and psychological mapping relation model, so as to obtain the mapping relation between the physiological parameters and psychological parameters output by the physiological and psychological mapping relation model, and the weight corresponding to each mapping relation.
Step S206: and inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk assessment model to carry out risk assessment, so as to obtain a risk assessment value of coal mine operators to be assessed.
In step S206, the risk assessment process by the human factor accident risk assessment model mainly includes the following steps:
step S21: and carrying out weighted calculation according to the physiological parameters, the psychological parameters and the weights corresponding to the mapping relation to obtain a health evaluation value.
In step S21, the formula of the weight calculation may beH=aX+aYWherein, the method comprises the steps of, wherein,Has the health evaluation value, there was used,aas the weight of the material to be weighed,Xthe physiological parameter of the person is a function of the physiological parameter,Yis a psychological parameter.
It should be noted that the formula of the above weight calculation is merely illustrative and not limiting.
In an embodiment, the mapping relation between the multiple sets of physiological parameters and psychological parameters may be used to obtain multiple health evaluation values, which are respectively used to reflect health levels of different aspects of the coal mine operator, for example, the health evaluation values obtained by the two sets of mapping relation of heart rate-anxiety parameters and respiratory rate-anxiety parameters are all used to reflect psychological anxiety degree of the coal mine operator.
Step S22: and searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic.
In step S22, each risk performance feature is preset with a corresponding risk value, where the risk performance feature includes: without wearing a helmet, fatigue operation, operation distraction caused by anxiety, and the like.
In the specific implementation process of step S22, the risk behavior characteristics related to the sweet and sour psychology are found out assuming that the health evaluation value reflecting the sweet and sour psychology reaches the preset value.
Step S23: and if the human factor risk characteristic information contains the risk behavior characteristic, taking a preset risk value corresponding to the risk behavior characteristic as a behavior risk evaluation value.
In the specific implementation process of step S23, assuming that the health evaluation value of the coal mine worker reflects that the coal mine worker has a lucky mind, finding out that the corresponding risk behavior feature includes "not wearing a safety helmet", and the human factor risk feature information includes the feature of "not wearing a safety helmet", taking the risk value corresponding to "not wearing a safety helmet" as the risk evaluation value.
In one embodiment, if the coal mine operator has a plurality of risk performance characteristics included in the human factor risk characteristic information, the risk values of the plurality of risk performance characteristics are accumulated as the risk evaluation value.
Step S24: and determining the crowd category of the coal mine operator to be evaluated as the crowd category corresponding to the health evaluation value.
For example, if the health evaluation value representing the lucky mind is greater than the preset value, the corresponding crowd is the lucky mind crowd.
It should be noted that a coal mine operator may simultaneously correspond to a plurality of crowd categories, for example, belong to both the sweet and sour psychological crowd and the anxiety psychological crowd.
Step S25: searching for the risk nodes associated with the corresponding nodes of the crowd category in a pre-constructed knowledge graph, and searching for crowd risk evaluation values associated with the risk nodes.
For example, the risk nodes associated with the lucky psychological crowd comprise a person wearing no safety helmet, a person wearing no safety belt, a person wearing no breathing mask and the like, and the crowd risk evaluation values associated with the person wearing no safety helmet, the person wearing no safety belt, the person wearing no breathing mask and the like are accumulated to obtain a final crowd risk evaluation value.
Step S26: and coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value.
In step S26, the coupling process may be to multiply the behavioral risk assessment value and the crowd assessment value by corresponding scale coefficients, respectively, and then add them to obtain the risk assessment value.
It should be noted that the coupling process is merely illustrative and not limiting.
Step S207: and grading the risk level of the coal mine worker to be evaluated based on the risk evaluation value.
In the specific implementation process of step S207, if the risk assessment value is less than or equal to the preset value, it is determined that the risk level of the coal mine operator is low risk.
And if the risk assessment value exceeds within 10% of the preset value, determining the risk level of the coal mine operator as the medium risk.
And if the risk assessment value exceeds more than 10% of the preset value, determining that the risk level of the coal mine operator is high risk.
It should be noted that the above-mentioned rating process is merely illustrative and not limiting.
Step S208: and generating and outputting a risk assessment report containing identity information, post information and risk level for coal mine operators to be assessed.
Based on the risk assessment method for coal mine operators disclosed by the embodiment of the invention, the physiological parameters and the psychological parameters of the coal mine operators to be assessed are obtained, the mapping relation and the weight between the physiological parameters and the psychological parameters are determined, the human factor risk characteristic information is extracted from the history file, the human factor risk characteristic information, the mapping relation and the weight are input into a human factor accident risk assessment model for risk assessment, the risk assessment value of the coal mine operators to be assessed is obtained, the risk assessment value is used for carrying out rating based on the risk assessment value, and a risk assessment report containing the risk grade of the coal mine operators to be assessed is generated and output. According to the scheme, the risk assessment is carried out by utilizing the artificial accident risk assessment model based on the mapping relation between the psychological parameters and the physiological parameters of the coal mine operators to be assessed and the historical artificial risk characteristic information, so that the aim of rapidly and objectively assessing the coal mine operators is fulfilled, and the requirements of rapid screening of a plurality of coal mine operators are met.
Based on the risk assessment method for coal mine operators disclosed in the embodiment of the invention, correspondingly, as shown in fig. 3, a flowchart of a human-caused accident risk assessment model construction method disclosed in the embodiment of the invention is provided, and the method comprises the following steps:
step S301: and constructing a behavior evaluation sub-model containing a mapping relation between the risk behavior characteristics and the health evaluation value.
In step S301, the behavior evaluation sub-model corresponds to the worker behavior model of the corresponding embodiment of fig. 1, and the health evaluation value is input into the behavior evaluation sub-model to obtain risk behavior characteristics corresponding to the output of the behavior evaluation sub-model.
Step S302: and assigning a preset risk value corresponding to the risk behavior characteristic in the evaluation sub-model.
In step S302, after assigning a preset risk value corresponding to the risk behavior feature in the evaluation sub-model, a complete behavior evaluation sub-model is obtained, and at this time, a health evaluation value is input into the behavior evaluation sub-model, so that the behavior evaluation sub-model outputs a corresponding risk behavior feature and a corresponding behavior risk evaluation value.
Step S303: and constructing a crowd evaluation sub-model comprising a knowledge graph and a corresponding relation between crowd categories and health evaluation values.
In step S303, the crowd assessment sub-model corresponds to the artificial intelligence assessment model of the corresponding embodiment of FIG. 1.
The knowledge graph comprises the association relation between the crowd category nodes and the risk nodes and the association relation between the risk nodes and the crowd risk assessment value.
Step S304: and constructing a human factor accident risk assessment model comprising a behavior assessment sub-model and a crowd assessment sub-model.
In step S304, the human factor accident risk assessment model includes a coupling module, a behavior assessment sub-model and a crowd assessment sub-model, where the coupling module is configured to perform coupling analysis on the behavior risk assessment values and the crowd risk assessment values output by the behavior assessment sub-model and the crowd assessment sub-model, and obtain coupled risk assessment values.
After the human factor accident risk assessment model is obtained, model training is performed on the human factor accident risk assessment model, and the training process of the human factor accident risk assessment model is performed in steps S305 to S314.
Step S305: and (3) inputting the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators into a human factor accident risk assessment model.
In step S305, the mapping relationship between the physiological parameters and psychological parameters of the coal mine operator is obtained by inputting the physiological parameters and psychological parameters of the coal mine operator into the pre-constructed physiological and psychological mapping model.
The human factor risk characteristic information is extracted from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information.
Step S306: and carrying out weighted calculation according to the physiological parameters, the psychological parameters and the weights corresponding to the mapping relation to obtain a health evaluation value.
Step S307: and searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic.
Step S308: and if the human factor risk characteristic information contains the risk behavior characteristic, taking a preset risk value corresponding to the risk behavior characteristic as a behavior risk evaluation value.
Step S309: and determining the crowd category of the coal mine operator to be evaluated as the crowd category corresponding to the health evaluation value.
Step S310: searching for the risk nodes associated with the corresponding nodes of the crowd category in a pre-constructed knowledge graph, and searching for crowd risk evaluation values associated with the risk nodes.
Step S311: and coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value.
It should be noted that, the specific implementation process and explanation of step S305 to step S311 refer to the corresponding embodiment of fig. 2, and the explanation is not repeated here.
Step S312: whether the risk assessment value is accurate or not is determined, if yes, step S313 is executed, and if not, step S314 is executed.
In step S312, the process of determining whether the risk assessment value is accurate includes:
and obtaining risk assessment of manual assessment by an expert based on the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information.
If the difference value between the risk evaluation value and the artificial risk evaluation value is within the preset range, the risk evaluation value is determined to be accurate.
If the difference value between the risk evaluation value and the manual risk evaluation value is not in the preset range, the risk evaluation value is determined to be inaccurate.
Step S313: and obtaining the trained human factor accident risk assessment model.
Step S314: and continuously inputting the mapping relation between the physiological parameters and the psychological parameters of the next coal mine worker and the human factor risk characteristic information corresponding to the post information into a human factor accident risk assessment model for training until the output risk assessment value and the risk information are accurate.
Based on the risk assessment method for the coal mine operators disclosed by the embodiment of the invention, the artificial accident risk assessment model comprising the coupling module, the behavior assessment sub-model and the crowd assessment sub-model is constructed, and the artificial accident risk assessment model is trained, so that the trained artificial accident risk assessment model is obtained. In the scheme, the artificial factor accident risk assessment model is constructed and trained, so that the artificial factor accident risk assessment model is utilized to carry out risk assessment based on the mapping relation between psychological parameters and physiological parameters of coal mine operators to be assessed and historical artificial factor risk characteristic information, the purpose of rapidly and objectively assessing the coal mine operators is achieved, and the requirements of rapid screening of a plurality of coal mine operators are met.
Corresponding to the risk assessment method of the coal mine operators disclosed in the embodiment of the invention, the embodiment of the invention discloses a risk assessment system of the coal mine operators, as shown in fig. 4, and an architecture diagram of the risk assessment system of the coal mine operators is disclosed in the embodiment of the invention.
The risk assessment system of the coal mine worker comprises: an acquisition unit 401, a health detection unit 402, an extraction unit 403, a determination unit 404, an evaluation unit 405, a rating unit 406, and a generation unit 407.
Specifically, the acquiring unit 401 is configured to acquire identity information and post information of a coal mine operator to be evaluated; and respectively acquiring the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information corresponding to the post information from the historical accident report, the historical post information and the historical expert post analysis opinion.
The health detection unit 402 is configured to perform physiological and psychological health detection on coal mine operators to be evaluated, so as to obtain physiological parameters and psychological parameters.
In one embodiment, the health detection unit 402 includes:
the physiological detection subunit is used for detecting physiological health of the coal mine operators to be evaluated by utilizing the rapid pre-post health screening system to obtain various physiological parameters of the coal mine operators to be evaluated.
The psychological detection subunit is used for acquiring the questionnaire information filled in by the coal mine operators to be evaluated, and carrying out psychological analysis to obtain all psychological parameters of the coal mine operators to be evaluated.
The extracting unit 403 is configured to extract the human factor risk feature information from the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information.
In an embodiment, the extracting unit 403 is specifically configured to: the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information are input into a man-machine-ring interaction model to conduct feature analysis, and the human factor risk feature information representing the accident caused by human factors is extracted.
The determining unit 404 is configured to determine a mapping relationship between the physiological parameter and the psychological parameter and a weight corresponding to each mapping relationship based on a preset physiological and psychological mapping relationship.
The evaluation unit 405 is configured to input the mapping relationship and the human factor risk feature information into a pre-constructed human factor accident risk evaluation model to perform risk evaluation, so as to obtain a risk evaluation value of the coal mine operator to be evaluated.
The risk assessment process of the human factor accident risk assessment model comprises the following steps: and carrying out weighted calculation according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation to obtain health evaluation values, finding risk behavior characteristics corresponding to the health evaluation values from all preset risk behavior characteristics, taking a preset risk value corresponding to the risk behavior characteristics as a behavior risk evaluation value if the risk behavior characteristics are contained in the risk characteristic information, determining that the crowd class of the coal mine worker to be evaluated is the crowd class corresponding to the health evaluation value, finding out the risk node associated with the crowd class corresponding node in a pre-built knowledge graph, finding out the crowd risk evaluation value associated with the risk node, coupling the behavior risk evaluation value and the crowd evaluation value, and obtaining and outputting the risk evaluation value.
And the rating unit 406 is used for rating the risk level of the coal mine worker to be evaluated based on the risk evaluation value.
In an embodiment, the rating unit 406 is specifically configured to: if the risk assessment value is smaller than or equal to the preset value, determining that the risk level of the coal mine operator is low risk, if the risk assessment value exceeds within 10% of the preset value, determining that the risk level of the coal mine operator is medium risk, and if the risk assessment value exceeds more than 10% of the preset value, determining that the risk level of the coal mine operator is high risk.
The generating unit 407 is configured to generate and output a risk assessment report including identity information, post information and risk level for the coal mine operator to be assessed.
In one embodiment, the risk assessment system for coal mine operators further comprises:
the system comprises a building unit, a judging unit and a judging unit, wherein the building unit is used for building a behavior evaluation sub-model containing a mapping relation between risk behavior characteristics and health evaluation values, assigning a preset risk value corresponding to the risk behavior characteristics in the evaluation sub-model, building a crowd evaluation sub-model containing a knowledge graph and a corresponding relation between crowd categories and health evaluation values, the knowledge graph contains an association relation between crowd category nodes and risk nodes and an association relation between the risk nodes and the crowd risk evaluation values, and building a human factor accident risk evaluation model containing the behavior evaluation sub-model and the crowd evaluation sub-model.
In one embodiment, the risk assessment system for coal mine operators further comprises:
the training unit is used for inputting the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators into a human factor accident risk assessment model, carrying out weighted calculation according to the physiological parameters, the psychological parameters and the weights corresponding to the mapping relation to obtain a health assessment value, searching the risk behavior characteristics corresponding to the health assessment value from each preset risk behavior characteristic, taking the preset risk value corresponding to the risk behavior characteristics as a behavior risk assessment value if the human factor risk characteristic information contains the risk behavior characteristics, determining the crowd category of the coal mine operators to be assessed as the crowd category corresponding to the health assessment value, searching the crowd risk assessment value associated with the crowd category corresponding node in a pre-constructed knowledge graph, coupling the behavior risk assessment value and the crowd assessment value, obtaining and outputting the risk assessment value, judging whether the risk assessment value is accurate or not, obtaining a trained human factor accident assessment model if the risk assessment value is inaccurate, continuing to input the physiological parameters of the next coal mine operators and the crowd category corresponding to the crowd risk node corresponding to the health assessment value, and carrying out the risk factor information mapping till the risk factor information is accurate.
Based on the risk assessment system for coal mine operators disclosed by the embodiment of the invention, the physiological parameters and the psychological parameters of the coal mine operators to be assessed are obtained, the mapping relation and the weight between the physiological parameters and the psychological parameters are determined, the human factor risk characteristic information is extracted from the history file, the human factor risk characteristic information, the mapping relation and the weight are input into a human factor accident risk assessment model for risk assessment, the risk assessment value of the coal mine operators to be assessed is obtained, the risk assessment value is used for grading, and a risk assessment report containing the risk grade of the coal mine operators to be assessed is generated and output. According to the scheme, the risk assessment is carried out by utilizing the artificial accident risk assessment model based on the mapping relation between the psychological parameters and the physiological parameters of the coal mine operators to be assessed and the historical artificial risk characteristic information, so that the aim of rapidly and objectively assessing the coal mine operators is fulfilled, and the requirements of rapid screening of a plurality of coal mine operators are met.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system 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 purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A risk assessment method for coal mine operators, comprising:
acquiring identity information and post information of coal mine operators to be evaluated;
performing physiological and psychological health detection on the coal mine worker to be evaluated to obtain physiological parameters and psychological parameters;
respectively acquiring historical accident risk characteristic information, historical post risk characteristic information and historical environment risk characteristic information corresponding to the post information from a historical accident report, historical post information and historical expert post analysis opinion;
extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information;
determining the mapping relation between the physiological parameters and the psychological parameters and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation;
inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk assessment model for risk assessment to obtain a risk assessment value of the coal mine worker to be assessed;
ranking the risk level of the coal mine worker to be evaluated based on the risk evaluation value;
Generating and outputting a risk assessment report containing the identity information, the post information and the risk level for the coal mine worker to be assessed;
the risk assessment process of the human factor accident risk assessment model comprises the following steps:
according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value;
searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic;
if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value;
determining the crowd category of the coal mine worker to be evaluated as the crowd category corresponding to the health evaluation value;
searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node;
and coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value.
2. The method of claim 1, wherein the performing physiological and psychological health tests on the coal mine personnel to be assessed to obtain physiological and psychological parameters comprises:
Performing physiological health detection on the coal mine operators to be evaluated by using a rapid pre-post health screening system to obtain various physiological parameters of the coal mine operators to be evaluated;
and acquiring questionnaire investigation information filled by the coal mine operators to be evaluated, and performing psychological analysis to obtain all psychological parameters of the coal mine operators to be evaluated.
3. The method of claim 1, wherein extracting the human risk feature information from the historical accident risk feature information, the historical post risk feature information, and the historical environmental risk feature information comprises:
and inputting the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information into a man-machine-ring interaction model for feature analysis, and extracting human factor risk feature information representing the accident caused by human factors.
4. The method according to claim 1, wherein the process of constructing the human-caused accident risk assessment model comprises:
constructing a behavior evaluation submodel containing a mapping relation between risk behavior characteristics and health evaluation values;
assigning a preset risk value corresponding to the risk behavior characteristic in the evaluation sub-model;
Constructing a crowd evaluation submodel comprising a knowledge graph and a corresponding relation between crowd categories and health evaluation values; the knowledge graph comprises the association relation between crowd category nodes and risk nodes and the association relation between the risk nodes and crowd risk assessment values;
constructing a human factor accident risk assessment model comprising the behavior assessment sub-model and the crowd assessment sub-model;
the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators are input into the human factor accident risk assessment model;
according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value;
searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic;
if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value;
determining the crowd category of the coal mine operator as the crowd category corresponding to the health evaluation value;
searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node;
Coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value;
judging whether the risk evaluation value is accurate or not;
if the risk assessment value is accurate, obtaining a trained artificial accident risk assessment model;
if the risk assessment value is inaccurate, continuing to input the mapping relation between the physiological parameter and the psychological parameter of the next coal mine worker and the human factor risk characteristic information corresponding to the post information into the human factor accident risk assessment model for training until the output risk assessment value is accurate.
5. The method of claim 4, wherein said determining whether the risk assessment value is accurate comprises:
acquiring human factor risk characteristic information corresponding to post information and a mapping relation between physiological parameters and psychological parameters of coal mine operators by an expert to obtain an artificial risk evaluation value;
if the difference value between the risk evaluation value and the artificial risk evaluation value is within a preset range, determining that the risk evaluation value is accurate;
and if the difference value between the risk evaluation value and the artificial risk evaluation value is not in the preset range, determining that the risk evaluation value is inaccurate.
6. The method of claim 1, wherein the ranking the risk level of the coal mine personnel to be evaluated based on the risk assessment value comprises:
if the risk assessment value is smaller than or equal to a preset value, determining that the risk level of the coal mine operator to be assessed is low risk;
if the risk assessment value exceeds within 10% of a preset value, determining that the risk level of the coal mine operator to be assessed is a medium risk;
and if the risk assessment value exceeds more than 10% of a preset value, determining that the risk level of the coal mine operator to be assessed is high risk.
7. A risk assessment system for coal mine personnel, comprising:
the acquisition unit is used for acquiring identity information and post information of coal mine operators to be evaluated; respectively acquiring historical accident risk characteristic information, historical post risk characteristic information and historical environment risk characteristic information corresponding to the post information from a historical accident report, historical post information and historical expert post analysis opinion;
the health detection unit is used for detecting the physiological and psychological health of the coal mine operators to be evaluated to obtain physiological parameters and psychological parameters;
The extraction unit is used for extracting human factor risk characteristic information from the historical accident risk characteristic information, the historical post risk characteristic information and the historical environment risk characteristic information;
the determining unit is used for determining the mapping relation between the physiological parameter and the psychological parameter and the weight corresponding to each mapping relation based on the preset physiological and psychological mapping relation;
the evaluation unit is used for inputting the mapping relation and the human factor risk characteristic information into a pre-constructed human factor accident risk evaluation model to perform risk evaluation, so as to obtain a risk evaluation value of the coal mine worker to be evaluated; the risk assessment process of the human factor accident risk assessment model comprises the following steps: according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value; searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic; if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value; determining the crowd category of the coal mine worker to be evaluated as the crowd category corresponding to the health evaluation value; searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node; coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value;
The grading unit is used for grading the risk grade of the coal mine worker to be evaluated based on the risk evaluation value;
the generation unit is used for generating and outputting a risk assessment report containing the identity information, the post information and the risk level for the coal mine worker to be assessed.
8. The system of claim 7, wherein the health detection unit comprises:
the physiological detection subunit is used for detecting physiological health of the coal mine operators to be evaluated by utilizing a rapid pre-post health screening system to obtain various physiological parameters of the coal mine operators to be evaluated;
and the psychological detection subunit is used for acquiring the questionnaire information filled in by the coal mine operators to be evaluated, and carrying out psychological analysis to obtain all psychological parameters of the coal mine operators to be evaluated.
9. The system according to claim 7, wherein the extraction unit is specifically configured to:
and inputting the historical accident risk feature information, the historical post risk feature information and the historical environment risk feature information into a man-machine-ring interaction model for feature analysis, and extracting human factor risk feature information representing the accident caused by human factors.
10. The system of claim 7, further comprising:
the construction unit is used for constructing a behavior evaluation submodel containing a mapping relation between risk behavior characteristics and health evaluation values; assigning a preset risk value corresponding to the risk behavior characteristic in the evaluation sub-model; constructing a crowd evaluation submodel comprising a knowledge graph and a corresponding relation between crowd categories and health evaluation values; the knowledge graph comprises the association relation between crowd category nodes and risk nodes and the association relation between the risk nodes and crowd risk assessment values; constructing a human factor accident risk assessment model comprising the behavior assessment sub-model and the crowd assessment sub-model;
the training unit is used for inputting the mapping relation between the physiological parameters and the psychological parameters of the coal mine operators and the human factor risk characteristic information corresponding to the post information of the coal mine operators into the human factor accident risk assessment model; according to the physiological parameters, psychological parameters and weights corresponding to the mapping relation, carrying out weighted calculation to obtain a health evaluation value; searching risk behavior characteristics corresponding to the health evaluation value from each preset risk behavior characteristic; if the human factor risk feature information contains the risk behavior feature, taking a preset risk value corresponding to the risk behavior feature as a behavior risk evaluation value; determining the crowd category of the coal mine operator as the crowd category corresponding to the health evaluation value; searching a pre-constructed knowledge graph to obtain a risk node associated with a corresponding node of the crowd category, and searching a crowd risk evaluation value associated with the risk node; coupling the behavior risk evaluation value and the crowd evaluation value to obtain and output a risk evaluation value; judging whether the risk evaluation value is accurate or not; if the risk assessment value is accurate, obtaining a trained artificial accident risk assessment model; if the risk assessment value is inaccurate, continuing to input the mapping relation between the physiological parameter and the psychological parameter of the next coal mine worker and the human factor risk characteristic information corresponding to the post information into the human factor accident risk assessment model for training until the output risk assessment value is accurate.
CN202310835476.6A 2023-07-10 2023-07-10 Risk assessment method and system for coal mine operators Active CN116596320B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310835476.6A CN116596320B (en) 2023-07-10 2023-07-10 Risk assessment method and system for coal mine operators

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310835476.6A CN116596320B (en) 2023-07-10 2023-07-10 Risk assessment method and system for coal mine operators

Publications (2)

Publication Number Publication Date
CN116596320A CN116596320A (en) 2023-08-15
CN116596320B true CN116596320B (en) 2023-10-24

Family

ID=87590256

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310835476.6A Active CN116596320B (en) 2023-07-10 2023-07-10 Risk assessment method and system for coal mine operators

Country Status (1)

Country Link
CN (1) CN116596320B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810741A (en) * 2014-02-19 2014-05-21 重庆邮电大学 Underground emergency evacuation virtual crowd simulation method based on multiple intelligent agents
CN104605866A (en) * 2015-01-21 2015-05-13 中煤科工集团西安研究院有限公司 Miner physiological and psychological fatigue monitoring method based on electroencephalogram detection
CN104794575A (en) * 2015-04-21 2015-07-22 河南理工大学 Human factor risk early-warning system of enterprise
CN112884379A (en) * 2021-04-02 2021-06-01 辽宁工程技术大学 Method for predicting coal mine underground human factor safety risk
CN114912821A (en) * 2022-05-30 2022-08-16 上海迎智正能文化发展有限公司 Enterprise production human factor safety early warning and disposal management system and operation method thereof

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8548934B2 (en) * 2009-11-17 2013-10-01 Infozen, Inc. System and method for assessing risk
US9224096B2 (en) * 2012-01-08 2015-12-29 Imagistar Llc System and method for item self-assessment as being extant or displaced
WO2020255494A1 (en) * 2019-06-17 2020-12-24 日本電気株式会社 Risk estimation device, risk estimation method, computer program and recording medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810741A (en) * 2014-02-19 2014-05-21 重庆邮电大学 Underground emergency evacuation virtual crowd simulation method based on multiple intelligent agents
CN104605866A (en) * 2015-01-21 2015-05-13 中煤科工集团西安研究院有限公司 Miner physiological and psychological fatigue monitoring method based on electroencephalogram detection
CN104794575A (en) * 2015-04-21 2015-07-22 河南理工大学 Human factor risk early-warning system of enterprise
CN112884379A (en) * 2021-04-02 2021-06-01 辽宁工程技术大学 Method for predicting coal mine underground human factor safety risk
CN114912821A (en) * 2022-05-30 2022-08-16 上海迎智正能文化发展有限公司 Enterprise production human factor safety early warning and disposal management system and operation method thereof

Also Published As

Publication number Publication date
CN116596320A (en) 2023-08-15

Similar Documents

Publication Publication Date Title
Havlikova et al. Human reliability in man-machine systems
CN110598786B (en) Neural network training method, semantic classification method and semantic classification device
US20190114939A1 (en) Situational Awareness Analysis and Fatigue Management System
CN113762104A (en) Scene awareness evaluation method and device based on electroencephalogram signals and electronic equipment
CN112527821A (en) Student bloom mastery degree evaluation method, system and storage medium
CN103198230A (en) Method and system for detecting man-machine interfaces
CN110826852A (en) Risk assessment method and system for forced isolation drug rehabilitation personnel
CN108899089A (en) psychological assessment service system
CN114388103A (en) Algorithm for teenager psychological early warning analysis
Trabelsi et al. The emotional machine: A machine learning approach to online prediction of user's emotion and intensity
CN116596320B (en) Risk assessment method and system for coal mine operators
Maslovskyi et al. Adaptive test system of student knowledge based on neural networks
Okike et al. Problem solving and decision making: Consideration of individual differences in computer programming skills using myers briggs type indicator (mbti) and chidamber and kemerer java metrics (ckjm)
Deng et al. Group management model for construction workers' unsafe behavior based on cognitive process model
CN116725501A (en) Underground and shielded space rescue personnel state monitoring system efficiency evaluation method
CN114783552A (en) Method and system for detecting fatigue of operator before post
EP3255593A1 (en) Performance analysing and forecasting system
Griffith et al. Sleep-deprivation effect on human performance: a meta-analysis approach
KR101918359B1 (en) A Data Processing System Using AI
Strigini Engineering judgement in reliability and safety and its limits: what can we learn from research in psychology?
Zhang et al. Workload evaluation model of nuclear power plant operator in integrated system validation
Choi et al. Forecasting personal learning performance in virtual reality-based construction safety training using biometric responses
Alharyout et al. Confirmatory factor analysis of big five personality factors (CFA-BFPF)
Nguyen et al. A Sensor-Based Empirical Framework to Measure Construction Labor Productivity
Ćosić et al. The concept for assessment of pilot mental readiness training

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