CN119204686A - A construction worker safety risk assessment and early warning method, device and equipment - Google Patents
A construction worker safety risk assessment and early warning method, device and equipment Download PDFInfo
- Publication number
- CN119204686A CN119204686A CN202411403991.8A CN202411403991A CN119204686A CN 119204686 A CN119204686 A CN 119204686A CN 202411403991 A CN202411403991 A CN 202411403991A CN 119204686 A CN119204686 A CN 119204686A
- Authority
- CN
- China
- Prior art keywords
- construction
- safety risk
- data
- risk assessment
- early warning
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a construction operator safety risk assessment and early warning method, a device and equipment, which are used for inputting input data into a construction operator safety risk assessment model by acquiring attribute data and construction site behavior data of construction operators, the method comprises the steps of obtaining multidimensional characteristic values of input variables, carrying out cluster analysis on the multidimensional characteristic values to obtain safety risk classification of construction operators, and generating early warning indication of the safety risk of the construction operators according to the safety risk classification of the construction operators. By comprehensively analyzing multiple dimensions of constructors and inputting data into the security risk assessment model, the system can mine data features of different dimensions and identify potential safety hazards of constructors.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a construction worker safety risk assessment and early warning method, device and equipment.
Background
With the increasing size and number of construction projects, the safety management of construction sites is becoming an important research field. In order to scientifically evaluate the safety capability of construction operators, a plurality of research practices exist in the prior art, such as the safety capability of construction operators is matched with the post requirements, a capability evaluation system is designed, an accident emergency preparation capability evaluation index system is provided based on a scene-task-capability analysis model, an electric power enterprise operator safety capability evaluation system is constructed based on an energy post matching principle so as to ensure the matching of employee characteristics and the requirements of the operation tasks, in addition, technical means such as the Internet of things, big data and artificial intelligence are introduced along with the development of an intelligent technology, real-time dynamic early warning is attempted to be realized on an operation site, the influence of environmental factors on the safety behavior is considered, an environment dynamic early warning system is developed, and a construction information platform is built through the Internet of things technology so as to realize real-time acquisition, transmission and judgment of environment data.
Although some research progress has been made in the aspect of construction worker safety risk assessment at present, the following technical problems still exist in the prior art:
1. The assessment dimension is not comprehensive enough, the prior art is often focused on the assessment of safety knowledge and skills, and key factors such as safety consciousness, behavior habit and the like are ignored;
2. The lack of unification and quantification of the evaluation criteria affects the fairness and accuracy of the evaluation results;
3. The evaluation mode is traditional, relies on questionnaire investigation or field observation, is complex to operate and high in cost, and is difficult to popularize and apply on a large scale on a construction site.
In addition, at present, the safety supervision of many construction projects still adopts a manual management mode, constructors only need to simply register when entering the site, the follow-up operation behavior lacks effective supervision, and accidents caused by misoperation are easy to occur.
Disclosure of Invention
In view of the above, the application provides a construction operator security risk assessment and early warning method, which solves the technical problems that in the prior art, each area is mainly obtained by a line loss rate calculation formula, then is analyzed according to a manually set reasonable line loss rate, lacks scientific basis, has higher error and is difficult to realize fine management.
According to a first aspect of the application, there is provided a construction worker safety risk assessment and early warning method, comprising:
Acquiring attribute data and construction site behavior data of construction operators as input data;
inputting the input data into a construction worker safety risk assessment model to obtain a multidimensional characteristic value of an input variable;
performing cluster analysis on the multidimensional characteristic values to obtain safety risk classification of construction operators;
And generating early warning indication of the safety risk of the construction operators according to the safety risk classification of the construction operators.
According to a second aspect of the present application, there is provided a construction worker safety risk assessment and early warning device, comprising:
The acquisition module is used for acquiring attribute data of construction operators and behavior data of construction sites as input data;
the computing module is used for inputting the input data into a construction worker safety risk assessment model so as to acquire a multidimensional characteristic value of the input variable;
The classification module is used for carrying out cluster analysis on the multidimensional characteristic values so as to obtain the safety risk classification of construction operators;
and the alarm module is used for generating early warning indication of the safety risk of the construction worker according to the safety risk classification of the construction worker.
According to a third aspect of the present application, there is provided a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the construction worker safety risk assessment and early warning method described above when executing the computer program.
By means of the technical scheme, the construction operator safety risk assessment early warning method, the construction operator safety risk assessment early warning device and the construction site behavior data are obtained, the attribute data and the construction site behavior data of construction operators are used as input data, the input data are input into a construction operator safety risk assessment model to obtain multi-dimensional characteristic values of input variables, clustering analysis is conducted on the multi-dimensional characteristic values to obtain construction operator safety risk classification, and safety risk early warning indication of the construction operators is generated according to the construction operator safety risk classification. By comprehensively analyzing multiple dimensions of constructors and inputting data into the security risk assessment model, the system can mine data features of different dimensions and identify potential safety hazards of constructors.
The foregoing description is only an overview of the present application, and is intended to provide a better understanding of the technical means of the present application, and is to be construed as being a complete description of the present application, as well as the following detailed description of the present application, in order to provide further understanding of the present application with the aid of the appended claims.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
fig. 1 is a schematic diagram of an application scenario of a construction worker safety risk assessment and early warning method according to an embodiment of the present application;
Fig. 2 is a schematic flow chart of a construction worker safety risk assessment and early warning method according to an embodiment of the present application;
FIG. 3 shows a flow diagram of an improved DBSCAN density clustering algorithm provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of a construction worker safety risk assessment and early warning device according to an embodiment of the present application.
Detailed Description
Hereinafter, a specific embodiment of the present application will be described in detail with reference to the accompanying drawings in combination with examples. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
The method for evaluating and early warning the safety risk of the construction worker provided by the embodiment of the invention can be applied to the scene shown in fig. 1, and a manager needs to know the safety condition of each construction worker and the behavior record of each construction worker in real time so as to ensure the construction safety and prevent potential accidents, and in order to achieve the aim, the system evaluates and early warns the safety risk by collecting the following data sources:
And the construction site behavior data is obtained by collecting site behavior data of constructors in real time, such as equipment operation records, card swiping records of entering and exiting the construction site, safety helmet wearing conditions, real-time position tracking and the like. From these data, the current working state of the constructor can be known.
The construction site historical behavior database stores past behavior records of constructors, including past equipment operation, illegal behavior records, situations of participating in security training, past assessment results and the like. The historical data provides a reference for subsequent safety evaluation and helps analyze whether construction personnel have potential safety hazards.
The construction operator attribute database contains basic information and attributes of the construction operator, such as age, certificate qualification, job type, job age, health condition, etc. By analyzing the attribute data, the system can judge whether each worker meets the post requirements or has health and safety risks.
The server serves as a core hub for data processing, receives real-time and historical data from different data sources, and inputs the data into a pre-constructed security risk assessment model. By acquiring attribute data and construction site behavior data of construction operators, the construction operator safety risk assessment early warning method inputs the input data into a construction operator safety risk assessment model to acquire multidimensional characteristic values of input variables, performs cluster analysis on the multidimensional characteristic values to acquire construction operator safety risk classification, and generates construction operator safety risk early warning instructions according to the construction operator safety risk classification. By comprehensively analyzing multiple dimensions of constructors and inputting data into the security risk assessment model, the system can mine data features of different dimensions and identify potential safety hazards of constructors.
The present invention will be described in detail with reference to specific examples.
Embodiment one:
As shown in fig. 2, the method for evaluating and early warning safety risk of construction operators provided in the embodiment of the invention includes:
step 201, acquiring attribute data and construction site behavior data of construction operators as input data;
Step 202, inputting input data into a construction worker safety risk assessment model to obtain a multidimensional characteristic value of an input variable;
step 203, performing cluster analysis on the multidimensional feature values to obtain the safety risk classification of construction operators;
And 204, generating a construction worker safety risk early warning indication according to the construction worker safety risk classification.
According to the construction worker safety risk assessment and early warning method, attribute data and construction site behavior data of construction workers are obtained and used as input data, the input data are input into a construction worker safety risk assessment model to obtain multi-dimensional characteristic values of input variables, clustering analysis is conducted on the multi-dimensional characteristic values to obtain construction worker safety risk classification, and safety risk early warning instructions of the construction workers are generated according to the construction worker safety risk classification. By comprehensively analyzing multiple dimensions of constructors and inputting data into the security risk assessment model, the system can mine data features of different dimensions and identify potential safety hazards of constructors.
Embodiment two:
step 202 is preceded by a training process including a construction worker safety risk assessment model, including:
202-1, acquiring attribute data of construction operators and historical behavior data of construction sites, and creating a data set;
The method comprises the steps of obtaining attribute data S of construction operators and construction site historical behavior data X, wherein the attribute data of the construction operators comprise construction operator certificate qualification scores, construction operator entrance security training scores and construction operator violation behavior scores, and the construction site historical behavior data comprise construction time periods, construction point identifiers and construction types;
Based on the attribute data S of the construction operator and the construction site historical behavior data X, an N-dimensional tensor is constructed for a single sample (S: X), wherein N=N s+Nx,Ns is the dimension of the attribute data of the construction operator, and N x is the dimension of the construction site historical behavior data.
202-2, Preprocessing a data set, and dividing a training set and a testing set;
202-3, constructing a deep convolutional neural network model, acquiring a multidimensional characteristic value of an input variable, and performing cluster analysis on the multidimensional characteristic value to acquire corresponding classified output;
the method comprises the steps of constructing a deep convolutional neural network model, extracting constructor attribute features, construction behavior periodic variation features and construction violation behavior features by using a multi-layer convolutional kernel, performing cluster analysis on feature values by adopting a DBSCAN density clustering algorithm, and identifying safety risk classification of constructors.
Step 202-4, training and testing the deep convolutional neural network model using the created data set.
The deep convolutional neural network model is trained and optimized through a random gradient descent algorithm SGD, a cross entropy loss function is adopted as a loss function, and network parameters are adjusted in the training process to improve model classification accuracy.
In the second embodiment of the invention, the DBSCAN density clustering algorithm is adopted to perform cluster analysis on the characteristic values, the number of clusters is not required to be preset, and the clusters can be automatically formed according to the density of the data. By analyzing the multidimensional characteristic values (such as violation records, equipment operating frequency, working hour data and the like) of constructors, the algorithm can automatically identify the person with higher safety risk (such as the person with the violation behaviors or the person in the high-risk area for a long time) and classify the person as the high-risk person. Compared with the traditional method, the automatic clustering process reduces human intervention and improves the recognition accuracy. The data at the construction site often has some noise or abnormal points (such as abnormal records caused by equipment failure or temporary personnel behavior data). DBSCAN can automatically identify and eliminate noise points by setting reasonable minimum points MinPts and radius epsilon. The method can adaptively adjust the classification standard in different construction scenes (such as different work types and different project scales) to identify constructors with similar risk characteristics, and has wide applicability and can meet the safety evaluation requirements of different projects.
Embodiment III:
Behavior data at a construction site often contains a large amount of noise and abnormal points such as abnormal records caused by equipment failure, irregular operation behaviors, and the like. The noise points are easily classified as normal behavior points by mistake in the dense data by the traditional DBSCAN, so that the clustering result is inaccurate, as shown in fig. 3, an improved DBSCAN density clustering algorithm is introduced in the third embodiment of the invention, and correspondingly, the step of performing cluster analysis on the characteristic values by adopting the DBSCAN density clustering algorithm in the step 202-3 comprises the following steps:
Step 202-31, initializing a first distance threshold epsilon 1, a second distance threshold epsilon 2 and a minimum neighbor number MinPts;
wherein, epsilon 1 is smaller than epsilon 2,ε1 and corresponds to a first neighborhood and a high-density core point, epsilon 2 corresponds to a second domain and a low-density core point, and the calculating steps of the double-threshold parameter and the minimum neighbor number MinPts comprise:
counting the characteristic values, generating a histogram, and recording the occurrence frequency of each characteristic value;
Dividing the characteristic value into a high-density region and a low-density region according to the occurrence frequency of the characteristic value;
Setting a first distance threshold epsilon 1 for the high-density region and a second distance threshold epsilon 2 for the low-density region;
The first minimum number of neighbors MinPts 1 is set for the high-density region, and the second minimum number of neighbors MinPts 2 is set for the low-density region.
202-32, Randomly selecting an unprocessed sample point P in the data set, judging whether the P is a high-density core point, if the number of the sample points in a first neighborhood of the P is greater than or equal to MinPts, marking the point as the high-density core point, and starting cluster expansion;
202-33, marking all points in the neighborhood of the core point as the same class according to the type of the core point, continuously expanding the neighborhood of all the core points in the neighborhood and adding unprocessed points into the corresponding class;
steps 202-34, for points that do not belong to any core point neighborhood, mark as noise points.
In a construction scenario, some potentially high risk actions may not occur frequently, but have a significant impact on safety. The dual threshold mechanism of DBSCAN (the high density region uses a smaller neighborhood epsilon 1 and the low density region uses a larger neighborhood epsilon 2) can effectively identify low frequency but important potential high risk behaviors such as occasional illegal operations or irregular use of critical equipment, and early warning is sent out to these hidden dangers in time.
According to the embodiment of the invention, through the distance calculation based on the histogram, the overall calculated amount is reduced, the clustering efficiency is improved, the method is suitable for large-scale construction behavior data, the double-threshold mechanism can distinguish high-frequency and low-frequency risk behaviors, so that the model can more accurately identify core points and boundary points, errors are reduced, the improved method can more rapidly process data streams of a construction site, and the risk behaviors are effectively identified and early warned in time.
Further, as a specific implementation of the method of fig. 2 to 3, in an embodiment of the present invention, there is provided a construction worker security risk assessment and early warning device, as shown in fig. 4, including:
the acquisition module 410 is used for acquiring attribute data of construction operators and behavior data of construction sites as input data;
The calculation module 420 is configured to input the input data into a construction worker safety risk assessment model to obtain a multidimensional feature value of the input variable;
the classification module 430 is configured to perform cluster analysis on the multidimensional feature values to obtain a security risk classification of the construction worker;
the alarm module 440 is configured to generate a construction worker safety risk early warning indication according to the construction worker safety risk classification.
The embodiment of the invention provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of a construction worker safety risk assessment early warning method, and the method comprises the following steps:
Acquiring attribute data and construction site behavior data of construction operators as input data;
inputting the input data into a construction worker safety risk assessment model to obtain a multidimensional characteristic value of an input variable;
performing cluster analysis on the multidimensional characteristic values to obtain safety risk classification of construction operators;
And generating early warning indication of the safety risk of the construction operators according to the safety risk classification of the construction operators.
It should be noted that, in the foregoing embodiments, only the principle and implementation steps of the embodiments of the present invention are illustrated by using security risk assessment of construction operators, and the actual application scenario is not limited specifically, and the present invention is also applicable to other scenarios where real-time security monitoring and risk management are required, such as security management of industrial production, security management of electric power and energy industries, logistics and storage management, etc., and the functions or steps that can be implemented by the computer readable storage medium or the computer device may be correspondingly referred to the foregoing method embodiments, so that the description will not be repeated here.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The foregoing embodiments are merely illustrative of the technical solutions of the present invention, and not restrictive, and although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that modifications may still be made to the technical solutions described in the foregoing embodiments or equivalent substitutions of some technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The construction worker safety risk assessment and early warning method is characterized by comprising the following steps of:
Acquiring attribute data and construction site behavior data of construction operators as input data;
inputting the input data into a construction worker safety risk assessment model to obtain a multidimensional characteristic value of an input variable;
Performing cluster analysis on the multidimensional characteristic values to obtain construction worker safety risk classification;
And generating early warning indication of the safety risk of the construction operators according to the safety risk classification of the construction operators.
2. The construction worker safety risk assessment warning method according to claim 1, wherein before the step of inputting the input data into the construction worker safety risk assessment model to obtain the multidimensional characteristic value of the input variable, comprising:
acquiring attribute data of construction operators and historical behavior data of construction sites, and creating a data set;
Preprocessing a data set, and dividing a training set and a testing set;
Constructing a deep convolutional neural network model, acquiring a multidimensional characteristic value of an input variable, and performing cluster analysis on the multidimensional characteristic value to acquire corresponding classified output;
the deep convolutional neural network model is trained and tested using the created dataset.
3. The construction worker safety risk assessment and early warning method according to claim 2, wherein the step of acquiring attribute data and construction site history behavior data of the construction worker and creating a data set includes:
acquiring attribute data S of construction operators and construction site historical behavior data X, wherein the attribute data of the construction operators comprise construction operator certificate qualification scores, construction operator entrance security training scores and construction operator violation behavior scores, and the construction site historical behavior data comprise construction time periods, construction point identifiers and construction types;
Based on the attribute data S of the construction operator and the construction site historical behavior data X, an N-dimensional tensor is constructed for a single sample (S: X), wherein N=N s+Nx,Ns is the dimension of the attribute data of the construction operator, and N x is the dimension of the construction site historical behavior data.
4. The construction worker safety risk assessment and early warning method according to claim 2, wherein the step of constructing a deep convolutional neural network model, obtaining a multidimensional feature value of an input variable, and performing cluster analysis on the multidimensional feature value to obtain a corresponding classified output comprises the steps of:
and constructing a deep convolutional neural network model, extracting constructor attribute features, construction behavior periodic variation features and construction violation behavior features by using a multi-layer convolutional kernel, performing cluster analysis on feature values by adopting a DBSCAN density clustering algorithm, and identifying the safety risk classification of constructors.
5. The construction worker safety risk assessment pre-warning method according to claim 2, wherein the step of training and testing the deep convolutional neural network model using the created data set comprises:
Training and optimizing the deep convolutional neural network model through a random gradient descent algorithm SGD, wherein a cross entropy loss function is adopted as a loss function, and network parameters are adjusted in the training process so as to improve the model classification accuracy.
6. The construction worker safety risk assessment and early warning method according to claim 4, wherein the step of performing cluster analysis on the feature values by using a DBSCAN density clustering algorithm comprises the steps of:
Initializing a first distance threshold epsilon 1, a second distance threshold epsilon 2 and a minimum neighbor number MinPts, wherein epsilon 1 is smaller than epsilon 2,ε1 and corresponds to a first neighborhood and a high-density core point, and epsilon 2 corresponds to a second domain and a low-density core point;
Randomly selecting an unprocessed sample point P in the data set, judging whether the P is a high-density core point, marking the point as the high-density core point if the number of the sample points in a first neighborhood of the P is greater than or equal to MinPts, and starting cluster expansion;
Marking all the points in the neighborhood of the core point as the same class according to the type of the core point, continuously expanding the neighborhood of all the core points in the neighborhood and adding unprocessed points into the corresponding class;
For points that do not belong to any core point neighborhood, they are labeled noise points.
7. The construction worker safety risk assessment warning method according to claim 6, wherein the step of initializing the first distance threshold epsilon 1, the second distance threshold epsilon 2, and the minimum neighbor number MinPts comprises:
counting the characteristic values, generating a histogram, and recording the occurrence frequency of each characteristic value;
Dividing the characteristic value into a high-density region and a low-density region according to the occurrence frequency of the characteristic value;
Setting a first distance threshold epsilon 1 for the high-density region and a second distance threshold epsilon 2 for the low-density region;
The first minimum number of neighbors MinPts 1 is set for the high-density region, and the second minimum number of neighbors MinPts 2 is set for the low-density region.
8. The utility model provides a construction operation personnel security risk aassessment early warning device which characterized in that includes:
The acquisition module is used for acquiring attribute data of construction operators and behavior data of construction sites as input data;
the computing module is used for inputting the input data into a construction worker safety risk assessment model so as to acquire a multidimensional characteristic value of the input variable;
the classification module is used for carrying out cluster analysis on the multidimensional characteristic values so as to obtain the safety risk classification of construction operators;
and the alarm module is used for generating early warning indication of the safety risk of the construction worker according to the safety risk classification of the construction worker.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the construction worker safety risk assessment warning method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the construction worker safety risk assessment warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411403991.8A CN119204686A (en) | 2024-10-09 | 2024-10-09 | A construction worker safety risk assessment and early warning method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411403991.8A CN119204686A (en) | 2024-10-09 | 2024-10-09 | A construction worker safety risk assessment and early warning method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119204686A true CN119204686A (en) | 2024-12-27 |
Family
ID=94054296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411403991.8A Pending CN119204686A (en) | 2024-10-09 | 2024-10-09 | A construction worker safety risk assessment and early warning method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119204686A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120013261A (en) * | 2025-04-21 | 2025-05-16 | 北京尚博信科技有限公司 | A construction safety monitoring method and system based on CV large model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493375A (en) * | 2022-04-02 | 2022-05-13 | 清华大学 | Construction Safety Macro Evaluation System and Method |
| CN115392407A (en) * | 2022-10-28 | 2022-11-25 | 中建五局第三建设有限公司 | Method, device, equipment and medium for warning danger source based on unsupervised learning |
| CN117456398A (en) * | 2022-07-15 | 2024-01-26 | 中国石油化工股份有限公司 | Image recognition methods, devices, electronic equipment and storage media for high-risk operations in gas stations |
-
2024
- 2024-10-09 CN CN202411403991.8A patent/CN119204686A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493375A (en) * | 2022-04-02 | 2022-05-13 | 清华大学 | Construction Safety Macro Evaluation System and Method |
| CN117456398A (en) * | 2022-07-15 | 2024-01-26 | 中国石油化工股份有限公司 | Image recognition methods, devices, electronic equipment and storage media for high-risk operations in gas stations |
| CN115392407A (en) * | 2022-10-28 | 2022-11-25 | 中建五局第三建设有限公司 | Method, device, equipment and medium for warning danger source based on unsupervised learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120013261A (en) * | 2025-04-21 | 2025-05-16 | 北京尚博信科技有限公司 | A construction safety monitoring method and system based on CV large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lai et al. | Online pattern matching and prediction of incoming alarm floods | |
| EP3157264B1 (en) | Multi-sensor data summarization | |
| CN113570200B (en) | Power grid running state monitoring method and system based on multidimensional information | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN114448657B (en) | Distribution communication network security situation awareness and abnormal intrusion detection method | |
| CN119204686A (en) | A construction worker safety risk assessment and early warning method, device and equipment | |
| CN115409066A (en) | Time series data anomaly detection method, device and computer storage medium | |
| CN117768220B (en) | Network security level protection evaluation method, system and device based on artificial intelligence | |
| Azhari et al. | Detection of pulsar candidates using bagging method | |
| CN119599442A (en) | BIM-assisted steel structure construction safety management early warning method, device and equipment | |
| CN119475108A (en) | Charging pile fault diagnosis method, device, equipment and storage medium | |
| Liu et al. | Early warning control model and simulation study of engineering safety risk based on a convolutional neural network | |
| Awadid et al. | AI systems trustworthiness assessment: State of the art | |
| CN120087745A (en) | A quality safety risk management system for engineering construction | |
| CN114493899A (en) | Method and system for constructing classification prediction model of authenticable state | |
| Kang et al. | Evaluating artificial intelligence tools for automated practice conformance checking | |
| CN120046992B (en) | A method and system for auditing information processing of enterprise data assets | |
| CN116757336B (en) | Track traffic risk prediction method and system based on data driving | |
| Mowafy et al. | Building unstructured crime data prediction model: practical approach | |
| CN119721030B (en) | Automatic identification method and system for power grid operation violation codes | |
| CN116863481B (en) | Service session risk processing method based on deep learning | |
| CN119863117A (en) | Operation high risk identification and early warning method based on artificial intelligence technology | |
| CN119652552A (en) | Security baseline trust evaluation method and system based on user behavior | |
| Wolny | ANOMALY DETECTION IN UNIVARIATE TIME SERIES USING A MULTI-CRITERIA APPROACH. | |
| CN120030407A (en) | A method and device for key object classification based on multivariate asynchronous sequence data |
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 |