CN117455245A - Intelligent risk assessment system for enterprise safety production - Google Patents
Intelligent risk assessment system for enterprise safety production Download PDFInfo
- Publication number
- CN117455245A CN117455245A CN202311774118.5A CN202311774118A CN117455245A CN 117455245 A CN117455245 A CN 117455245A CN 202311774118 A CN202311774118 A CN 202311774118A CN 117455245 A CN117455245 A CN 117455245A
- Authority
- CN
- China
- Prior art keywords
- module
- risk
- early warning
- data
- threshold
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 38
- 238000012502 risk assessment Methods 0.000 title claims description 46
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000003066 decision tree Methods 0.000 claims description 45
- 230000004044 response Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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—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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk intelligent assessment system for enterprise safety production, which belongs to the technical field of risk intelligent assessment systems and comprises a data real-time acquisition module, a data preprocessing module, a data storage module, a risk identification module, a feature extraction module, a model training module, a model assessment module, a risk grade module, a risk report module, a risk early warning module and an early warning notification module.
Description
Technical Field
The invention belongs to the technical field of risk intelligent assessment systems, and particularly relates to a risk intelligent assessment system for enterprise safety production.
Background
The enterprise risk assessment is carried out on collected risk management initial information, various business management and important business processes of an enterprise, and comprises three steps of risk identification, risk analysis and risk assessment, wherein the steps are aimed at searching and describing enterprise risks, assessing the influence degree and risk value of various identified risks on the realization of targets of the enterprise, giving priority of risk control and the like;
however, the existing risk assessment system has certain defects, the existing risk assessment system relies on manual data collection, risk analysis and control measure establishment, which may lead to inaccurate data, strong subjectivity in the analysis process and slow response speed, the assessment result is not comprehensive enough, the risk condition of enterprise safety production cannot be completely reflected, quantitative analysis and modeling of risk factors are lacking, the assessment result is not accurate enough, and an intelligent technology is lacking.
Disclosure of Invention
The invention aims to provide an intelligent risk assessment system for enterprise safety production, which is used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the intelligent risk assessment system for enterprise safety production comprises a data real-time acquisition module, a data preprocessing module, a data storage module, a risk identification module, a feature extraction module, a model training module, a model evaluation module, a risk assessment module, a risk level module, a risk report module, a risk early warning module, an early warning notification module, a training set module, a decision tree generation module, a feature taking module, a training decision tree module, a test set module, a set early warning threshold module, a risk monitoring module, a threshold judgment module, an early warning response module, an early warning recording module and a no early warning response module;
the data real-time acquisition module is responsible for establishing connection with an enterprise production system, and acquiring data related to safety production in real time according to set acquisition time;
the data acquisition module is in wireless connection with the data preprocessing module, the data acquisition module collects safety production data information according to the data real-time acquisition module, and the data preprocessing module performs processing operations such as further data conversion, integration and the like on the acquired data;
the risk recognition module extracts risk characteristics from the data storage module, performs machine learning algorithm training and recognizes safety risks by using a model;
the risk assessment module is in wireless connection with the risk early warning module, the risk assessment module analyzes and determines risk level, influence range and occurrence probability according to the risk identification module and generates a risk report, and the risk early warning module carries out early warning response and early warning notification when the risk level is predicted to exceed a preset threshold according to the risk identification module and records early warning information of each time.
The data acquisition module reads the data information of the enterprise production system according to the data real-time acquisition module, sets a data collection time interval, acquires data and transmits the data to the data acquisition module.
The data preprocessing module processes the acquired data and comprises a data cleaning module, a normalization module and a format conversion module;
the data cleaning module is used for cleaning the collected data, and the data cleaning module is used for processing the problems of errors, missing, repetition and abnormality in the original data;
wherein the normalization and normalization converts data of different scales, units or distributions into the same range, such that different features are comparable;
the format conversion module converts the processed data into a format, and ensures that the formats are consistent in the data transmission process.
The risk identification module specifically operates the method, and the method comprises the following steps of;
a1: extracting features from the data storage module according to risk identification requirements;
a2: extracting a part of feature subsets from the extracted features;
a3: generating a decision tree according to the feature subset, wherein the feature number is limited when the node is split;
a4: training the selected decision tree by using training set data to obtain a model capable of identifying safety risks;
a5: and evaluating the trained model by using a test set, and continuing to optimize if the evaluation effect is poor.
Wherein in A3, a decision tree t is generated and a sample set of leaf nodes m is obtainedFor each sample->Its category label->Is the majority class of all samples, thus yielding the mth leaf node: the formula is:
(1),
in the formula (i) the formula (ii),representing the classification of samples x by the decision tree, |d_m| representing the total number of samples contained by the leaf node m;
in A4, the model consists of a plurality of decision trees, and for each decision tree t and sample x, the formula is:
(2),
in the formula, M represents the total number of samples contained in the leaf node where the sample x is located,a class label representing the mth sample contained in the leaf node, and representing the prediction result of the decision tree t on the sample x;
the prediction result f1 (x), f2 (x) of the sample x on each tree can be obtained according to the formula (2).And carrying out weighted average on the prediction result of each decision tree, wherein the formula is as follows:
(3),
in the formula, f (x) represents the final prediction result, and T represents the number of decision trees.
The test set is used for evaluating the trained model in A5, wherein the evaluation comprises accuracy, recall and F1 score, and the evaluation comprises the following algorithm:
(4)
in the formula (4) of the present invention,representing accuracy, TP representing a real instance, TN representing a real instanceNegative examples, FP represents false positive examples, FN represents false negative examples; the accuracy represents the proportion of the number of correct predictions to the total number of samples and is used for measuring the overall prediction accuracy of the model;
(5),
in the formula (5) of the present invention,representing a recall that is measured as correctly predicted as positive class among all positive classes;
(6),
in the formula (6),representing accuracy, representing positive classes in samples predicted to be positive classes;
the mean value F1 is reconciled by combining equation (5) and equation (6), the equation being:
(7),
in the formula, the F1 score combines the advantages of the accuracy and the recall, so that the performance of the model can be more comprehensively evaluated, when the accuracy and the recall are similar, the F1 score is close to the maximum value 1, the model performance is better, otherwise, if the accuracy or the recall is lower, the F1 score is correspondingly reduced.
The risk assessment module carries out risk assessment according to the model trained by the risk identification module, and comprises the following steps:
b1: evaluating the predicted result according to the risk factors identified by the risk identification module, and grading f (x) the final predicted result;
b2: generating a detailed risk report according to the risk identification and assessment results, wherein the report comprises the contents of risk factors, influence assessment, countermeasures and the like;
b3: setting an early warning threshold value threshold according to the risk level and the early warning standard data, and triggering a corresponding early warning level when the risk assessment result exceeds the threshold value;
b4: monitoring the risk threshold in real time, comparing the received risk assessment prediction result with the early warning threshold, and judging whether to trigger the early warning level;
b5: receiving an early warning signal from a threshold judging module, and performing early warning response and early warning notification when the risk level is greater than a threshold, wherein each early warning is recorded;
b6: receiving an early warning signal from a threshold judging module, and performing early warning-free response when the risk level does not reach a threshold;
in the step B4, the final prediction result of the step B1 is combined with the early warning threshold value set by the step B3 to be compared, and the formula is as follows:
(8),
(9),
in the formula, f (x) in the formula (8) represents a final prediction result, threshold represents an early warning threshold, epsilon represents an upper deviation parameter, and when f (x) exceeds the threshold plus a smaller upper deviation epsilon, the risk level is higher, and early warning is immediately triggered; equation (9) f (x) is below the threshold minus a small lower deviation δ, indicating a low risk level and no early warning response.
The risk assessment module and the risk early warning module can assess risks and predict risk results in real time, detect risk thresholds in real time, compare the risk thresholds with predicted results of risk grades, and respond to alarms when the predicted results exceed the set risk thresholds.
Compared with the prior art, the invention has the beneficial effects that:
1. the system can acquire and process related data of enterprise safety production in real time through the data real-time acquisition module, the data acquisition module and the data preprocessing module, ensures the accuracy and the integrity of the data, is beneficial to improving the accuracy and the instantaneity of risk assessment, and provides more reliable support for enterprise decision-making;
2. according to the invention, through the risk identification module and the feature extraction module, the system automatically identifies and extracts potential risks in enterprise safety production, and the model training module and the model evaluation module can train and evaluate the extracted features so as to improve the accuracy and stability of the model, thereby being beneficial to promoting standardization and standardization of enterprise risk management and improving the quality and efficiency of risk management;
3. according to the invention, the risk early warning module can automatically early warn the risk of enterprise safety production according to the output of the model evaluation module and the set early warning threshold value, and the early warning notification module can timely notify related personnel of early warning information, so that timely information transmission is ensured, and the enterprise can timely find and deal with potential risks;
4. according to the invention, through the risk monitoring module and the threshold judging module, the system can monitor the risk condition of enterprise safety production in real time and judge according to the set early warning threshold, thereby being beneficial to enhancing the controllability and stability of enterprise safety production and ensuring the safe operation of enterprises.
Drawings
FIG. 1 is a flow chart illustrating the operation of a risk intelligent assessment system for enterprise security production in accordance with the present invention;
FIG. 2 is a flow chart of the risk identification module class operation of the intelligent risk assessment system for enterprise safety production according to the present invention;
FIG. 3 is a flow chart of the operation of the risk assessment module of the intelligent risk assessment system for enterprise safety production according to 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.
Examples
Referring to fig. 1-3, the present invention provides a technical solution: the system comprises a data real-time acquisition module, a data preprocessing module, a data storage module, a risk identification module, a feature extraction module, a model training module, a model evaluation module, a risk assessment module, a risk level module, a risk report module, a risk early warning module, an early warning notification module, a training set module, a generation decision tree module, a feature taking module, a training decision tree module, a test set module, a pre-warning threshold setting module, a risk monitoring module, a threshold judging module, an early warning response module, an early warning recording module and a non-early warning response module;
the data real-time acquisition module is responsible for establishing connection with an enterprise production system, and acquiring data related to safety production in real time according to set acquisition time;
the data acquisition module is in wireless connection with the data preprocessing module, the data acquisition module collects safety production data information according to the data real-time acquisition module, and the data preprocessing module performs processing operations such as further data conversion, integration and the like on the acquired data;
the risk recognition module extracts risk characteristics from the data storage module, performs machine learning algorithm training and recognizes safety risks by using a model;
the risk assessment module is in wireless connection with the risk early warning module, the risk assessment module analyzes and determines risk level, influence range and occurrence probability according to the risk identification module and generates a risk report, and the risk early warning module carries out early warning response and early warning notification when the risk level is predicted to exceed a preset threshold according to the risk identification module and records early warning information of each time.
The data acquisition module reads the data information of the enterprise production system according to the data real-time acquisition module, sets a data collection time interval, acquires data and transmits the data to the data acquisition module.
The data preprocessing module processes the acquired data and comprises a data cleaning module, a normalization module and a format conversion module;
the data cleaning module is used for cleaning the collected data, and the data cleaning module is used for processing the problems of errors, missing, repetition and abnormality in the original data;
wherein the normalization and normalization converts data of different scales, units or distributions into the same range, such that different features are comparable;
the format conversion module converts the processed data into a format, and ensures that the formats are consistent in the data transmission process.
The risk identification module specifically operates the method, and the method comprises the following steps of;
a1: extracting features from the data storage module according to risk identification requirements;
a2: extracting a part of feature subsets from the extracted features;
a3: generating a decision tree according to the feature subset, wherein the feature number is limited when the node is split;
a4: training the selected decision tree by using training set data to obtain a model capable of identifying safety risks;
a5: and evaluating the trained model by using a test set, and continuing to optimize if the evaluation effect is poor.
Wherein in A3, a decision tree t is generated and a sample set of leaf nodes m is obtainedFor each sample->Class of the sameIdentifying label->Is the majority class of all samples, thus yielding the mth leaf node: the formula is:
(1),
in the formula (i) the formula (ii),representing the classification of samples x by the decision tree, |d_m| representing the total number of samples contained by the leaf node m;
in A4, the model consists of a plurality of decision trees, and for each decision tree t and sample x, the formula is:
(2),
in the formula, M represents the total number of samples contained in the leaf node where the sample x is located,a class label representing the mth sample contained in the leaf node, and representing the prediction result of the decision tree t on the sample x;
the prediction result f1 (x), f2 (x) of the sample x on each tree can be obtained according to the formula (2).And carrying out weighted average on the prediction result of each decision tree, wherein the formula is as follows:
(3),
in the formula, f (x) represents the final prediction result, and T represents the number of decision trees.
The test set is used for evaluating the trained model in A5, wherein the evaluation comprises accuracy, recall and F1 score, and the evaluation comprises the following algorithm:
(4)
in the formula (4) of the present invention,representing accuracy, TP represents a real case, TN represents a true negative case, FP represents a false positive case, and FN represents a false negative case; the accuracy represents the proportion of the number of correct predictions to the total number of samples and is used for measuring the overall prediction accuracy of the model;
(5),
in the formula (5) of the present invention,representing a recall that is measured as correctly predicted as positive class among all positive classes;
(6),
in the formula (6),representing accuracy, representing positive classes in samples predicted to be positive classes;
the mean value F1 is reconciled by combining equation (5) and equation (6), the equation being:
(7),
in the formula, the F1 score combines the advantages of the accuracy and the recall, so that the performance of the model can be more comprehensively evaluated, when the accuracy and the recall are similar, the F1 score is close to the maximum value 1, the model performance is better, otherwise, if the accuracy or the recall is lower, the F1 score is correspondingly reduced.
The risk assessment module carries out risk assessment according to the model trained by the risk identification module, and comprises the following steps:
b1: evaluating the predicted result according to the risk factors identified by the risk identification module, and grading f (x) the final predicted result;
b2: generating a detailed risk report according to the risk identification and assessment results, wherein the report comprises the contents of risk factors, influence assessment, countermeasures and the like;
b3: setting an early warning threshold value threshold according to the risk level and the early warning standard data, and triggering a corresponding early warning level when the risk assessment result exceeds the threshold value;
b4: monitoring the risk threshold in real time, comparing the received risk assessment prediction result with the early warning threshold, and judging whether to trigger the early warning level;
b5: receiving an early warning signal from a threshold judging module, and performing early warning response and early warning notification when the risk level is greater than a threshold, wherein each early warning is recorded;
b6: receiving an early warning signal from a threshold judging module, and performing early warning-free response when the risk level does not reach a threshold;
in the step B4, the final prediction result of the step B1 is combined with the early warning threshold value set by the step B3 to be compared, and the formula is as follows:
(8),
(9),
in the formula, f (x) in the formula (8) represents a final prediction result, threshold represents an early warning threshold, epsilon represents an upper deviation parameter, and when f (x) exceeds the threshold plus a smaller upper deviation epsilon, the risk level is higher, and early warning is immediately triggered; equation (9) f (x) is below the threshold minus a small lower deviation δ, indicating a low risk level and no early warning response.
The risk assessment module and the risk early warning module can assess risks and predict risk results in real time, detect risk thresholds in real time, compare the risk thresholds with predicted results of risk grades, and respond to alarms when the predicted results exceed the set risk thresholds.
In this example, specific: the specific operation method of the risk identification module comprises the following steps of;
a1: extracting features from the data storage module according to risk identification requirements;
a2: extracting a part of feature subsets from the extracted features;
a3: generating a decision tree according to the feature subset, wherein the feature number is limited when the node is split;
a4: training the selected decision tree by using training set data to obtain a model capable of identifying safety risks;
a5: and evaluating the trained model by using a test set, and continuing to optimize if the evaluation effect is poor.
Wherein in A3, a decision tree t is generated and a sample set of leaf nodes m is obtainedFor each sample->Its category label->Is the majority class of all samples, thus yielding the mth leaf node: the formula is:
(1),
in the formula (i) the formula (ii),representing the classification of samples x by the decision tree, |d_m| representing the total number of samples contained by the leaf node m;
in A4, the model consists of a plurality of decision trees, and for each decision tree t and sample x, the formula is:
(2),
in the formula, M represents the total number of samples contained in the leaf node where the sample x is located,a class label representing the mth sample contained in the leaf node, and representing the prediction result of the decision tree t on the sample x;
the prediction result f1 (x), f2 (x), of the sample x on each tree can be obtained according to formula (2),and carrying out weighted average on the prediction result of each decision tree, wherein the formula is as follows:
(3),
in the formula, f (x) represents the final prediction result, and T represents the number of decision trees.
In this example, specific: the test set is used in A5 to evaluate the trained model, including accuracy, recall and F1 score, including the following algorithms:
(4)
in the formula (4) of the present invention,representing accuracy, TP represents a real case, TN represents a true negative case, FP represents a false positive case, and FN represents a false negative case; the accuracy represents the proportion of the number of correct predictions to the total number of samples and is used for measuring the overall prediction accuracy of the model;
(5),
in the formula (5) of the present invention,representing a recall that measures how much of all positive classes are correctly predicted as positive classes;
(6),
in the formula (6),representing accuracy, representing how many of the samples predicted to be positive are actually positive classes;
the mean value F1 is reconciled by combining equation (5) and equation (6), the equation being:
(7),
in the formula, the F1 score combines the advantages of the accuracy and the recall, so that the performance of the model can be more comprehensively evaluated, when the accuracy and the recall are similar, the F1 score is close to the maximum value 1, the model performance is better, otherwise, if the accuracy or the recall is lower, the F1 score is correspondingly reduced.
In this example, specific: the risk assessment module carries out risk assessment according to the model trained by the risk identification module, and comprises the following steps:
b1: evaluating the predicted result according to the risk factors identified by the risk identification module, and grading f (x) the final predicted result;
b2: generating a detailed risk report according to the risk identification and assessment results, wherein the report comprises the contents of risk factors, influence assessment, countermeasures and the like;
b3: setting an early warning threshold value threshold according to the risk level and the early warning standard data, and triggering a corresponding early warning level when the risk assessment result exceeds the threshold value;
b4: monitoring the risk threshold in real time, comparing the received risk assessment prediction result with the early warning threshold, and judging whether to trigger the early warning level;
b5: receiving an early warning signal from a threshold judging module, and performing early warning response and early warning notification when the predicted result is greater than a threshold, wherein each early warning is recorded;
b6: receiving an early warning signal from a threshold judging module, and performing early warning-free response when the predicted result does not reach a threshold;
in the step B4, the final prediction result of the step B1 is combined with the early warning threshold value set by the step B3 to be compared, and the formula is as follows:
(8),
(9),
in the formula, f (x) in the formula (8) represents a final prediction result, threshold represents an early warning threshold, epsilon represents an upper deviation parameter, and when f (x) exceeds the threshold plus a smaller upper deviation epsilon, the risk level is higher, and early warning is immediately triggered; equation (9) f (x) is below the threshold minus a small lower deviation δ, indicating a low risk level and no early warning response.
Working principle: the data acquisition module is connected with the enterprise production system to acquire various data in the enterprise safety production process in real time, collects safety production data information according to the data real-time acquisition module, performs data preprocessing such as cleaning, standardization and normalization on the acquired data, and stores the cleaned data into the data storage module;
extracting representative features from the preprocessed data according to the requirements of risk identification, providing input for model training, providing a standard training dataset, generating a decision tree according to the extracted features, selecting the most representative and distinguishing features for constructing the decision tree, training a decision tree model by using the training dataset to realize risk identification, and evaluating the trained model by using a test set; and (3) carrying out risk assessment prediction results and grading according to the risk identification module, generating a risk report according to the prediction results, setting an early warning threshold according to the risk grade by risk early warning, carrying out risk monitoring, judging whether the current risk condition needs to send early warning or not according to the set early warning threshold, and carrying out early warning-free response when the risk grade exceeds the threshold, alarming and timely notifying record, wherein the risk grade does not exceed the threshold.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations may be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents.
The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (8)
1. A risk intelligence evaluation system for enterprise safety production which characterized in that: the system comprises a data real-time acquisition module, a data preprocessing module, a data storage module, a risk identification module, a feature extraction module, a model training module, a model evaluation module, a risk assessment module, a risk level module, a risk report module, a risk early warning module, an early warning notification module, a training set module, a generation decision tree module, a feature taking module, a training decision tree module, a test set module, a pre-warning threshold setting module, a risk monitoring module, a threshold judging module, an early warning response module, an early warning recording module and a non-early warning response module;
the data real-time acquisition module is responsible for establishing connection with an enterprise production system, and acquiring data related to safety production in real time according to set acquisition time;
the data acquisition module is in wireless connection with the data preprocessing module, the data acquisition module collects safety production data information according to the data real-time acquisition module, and the data preprocessing module performs processing operations such as further data conversion, integration and the like on the acquired data;
the risk recognition module extracts risk characteristics from the data storage module, performs machine learning algorithm training and recognizes safety risks by using a model;
the risk assessment module is in wireless connection with the risk early warning module, the risk assessment module analyzes and determines risk level, influence range and occurrence probability according to the risk identification module and generates a risk report, and the risk early warning module carries out early warning response and early warning notification when the risk level is predicted to exceed a preset threshold according to the risk identification module and records early warning information of each time.
2. A risk intelligent assessment system for enterprise security production as claimed in claim 1, wherein: and the data acquisition module reads the data information of the enterprise production system according to the data real-time acquisition module, sets a data collection time interval, and performs data acquisition and transmission to the data acquisition module.
3. A risk intelligent assessment system for enterprise security production as claimed in claim 1, wherein: the data preprocessing module processes the acquired data and comprises a data cleaning module, a standardization module, a normalization module and a format conversion module;
the data cleaning module is used for cleaning the collected data, and the data cleaning module is used for processing the problems of errors, missing, repetition and abnormality in the original data;
wherein the normalization and normalization converts data of different scales, units or distributions into the same range, such that different features are comparable;
the format conversion module converts the processed data into a format, and ensures that the formats are consistent in the data transmission process.
4. A risk intelligent assessment system for enterprise security production as claimed in claim 1, wherein: the specific operation method of the risk identification module comprises the following steps of;
a1: extracting features from the data storage module according to risk identification requirements;
a2: selecting a subset of features from the extracted features;
a3: generating a decision tree according to the feature subset, wherein the feature number is limited when the node is split;
a4: training the selected decision tree by using training set data to obtain a model capable of identifying safety risks;
a5: and evaluating the trained model by using the test set, and continuing training if the evaluation effect is poor.
5. The intelligent risk assessment system for enterprise security production of claim 4, wherein: in A3, a decision tree t is generated and a sample set of leaf nodes m is obtainedFor each sample->Its category label->Is the majority class of all samples, thus yielding the mth leaf node: the formula is:
(1),
in the formula,Representing the classification of samples x by the decision tree, |d_m| representing the total number of samples contained by the leaf node m;
in A4, the model consists of a plurality of decision trees, and for each decision tree t and sample x, the formula is:
(2),
in the formula, M represents the total number of samples contained in the leaf node where the sample x is located,a class label representing the mth sample contained in the leaf node, and representing the prediction result of the decision tree t on the sample x;
the prediction result f1 (x), f2 (x) of the sample x on each tree can be obtained according to the formula (2).And carrying out weighted average on the prediction result of each decision tree, wherein the formula is as follows:
(3),
in the formula, f (x) represents the final prediction result, and T represents the number of decision trees.
6. The intelligent risk assessment system for enterprise security production of claim 4, wherein: the test set is used in A5 to evaluate the trained model, including accuracy, recall and F1 score, including the following algorithms:
(4)
in the formula (4) of the present invention,representing accuracy, TP represents a real case, TN represents a true negative case, FP represents a false positive case, and FN represents a false negative case; the accuracy represents the proportion of the number of correct predictions to the total number of samples and is used for measuring the overall prediction accuracy of the model;
(5),
in the formula (5) of the present invention,representing a recall that is measured as correctly predicted as positive class among all positive classes;
(6),
in the formula (6),representing accuracy, representing positive classes in samples predicted to be positive classes;
the mean value F1 is reconciled by combining equation (5) and equation (6), the equation being:
(7),
in the formula, the F1 score combines the advantages of the accuracy and the recall, so that the performance of the model can be more comprehensively evaluated, when the accuracy and the recall are similar, the F1 score is close to the maximum value 1, the model performance is better, otherwise, if the accuracy or the recall is lower, the F1 score is correspondingly reduced.
7. The intelligent risk assessment system for enterprise security production of claim 5, wherein: the risk assessment module carries out risk assessment according to the model trained by the risk identification module, and comprises the following steps:
b1: evaluating the predicted result according to the risk factors identified by the risk identification module, and grading f (x) the final predicted result;
b2: generating a detailed risk report according to the risk identification and assessment results, wherein the report comprises the contents of risk factors, influence assessment, countermeasures and the like;
b3: setting an early warning threshold value threshold according to the risk level and the early warning standard data, and triggering a corresponding early warning level when the risk assessment result exceeds the threshold value;
b4: detecting a risk threshold in real time, comparing a received risk assessment prediction result with an early warning threshold, and judging whether to trigger an early warning level;
b5: receiving an early warning signal from a threshold judging module, and performing early warning response and early warning notification when the risk level is greater than a threshold, wherein each early warning is recorded;
b6: receiving an early warning signal from a threshold judging module, and performing early warning-free response when the risk level does not reach a threshold;
in the step B4, the final prediction result of the step B1 is combined with the early warning threshold value set by the step B3 to be compared, and the formula is as follows:
(8),
(9),
in the formula, f (x) in the formula (8) represents a final prediction result, threshold represents an early warning threshold, epsilon represents an upper deviation parameter, and when f (x) exceeds the threshold plus a smaller upper deviation epsilon, the risk level is higher, and early warning is immediately triggered; equation (9) f (x) is below the threshold minus a small lower deviation δ, indicating a low risk level and no early warning response.
8. A risk intelligence assessment system for enterprise security production as claimed in claim 7, wherein: the risk assessment module and the risk early warning module can assess risks and predict risk results in real time, detect risk thresholds in real time, compare the risk thresholds with predicted results of risk grades, and respond to alarms when the predicted results exceed the set risk thresholds.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311774118.5A CN117455245A (en) | 2023-12-22 | 2023-12-22 | Intelligent risk assessment system for enterprise safety production |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311774118.5A CN117455245A (en) | 2023-12-22 | 2023-12-22 | Intelligent risk assessment system for enterprise safety production |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117455245A true CN117455245A (en) | 2024-01-26 |
Family
ID=89589452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311774118.5A Pending CN117455245A (en) | 2023-12-22 | 2023-12-22 | Intelligent risk assessment system for enterprise safety production |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117455245A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118014373A (en) * | 2024-04-08 | 2024-05-10 | 中国汽车技术研究中心有限公司 | Risk identification model based on data quality monitoring and construction method thereof |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529327A (en) * | 2020-12-21 | 2021-03-19 | 北京建筑大学 | Method for constructing fire risk prediction grade model of buildings in commercial areas |
CN113159615A (en) * | 2021-05-10 | 2021-07-23 | 麦荣章 | Intelligent information security risk measuring system and method for industrial control system |
CN114499956A (en) * | 2021-12-24 | 2022-05-13 | 广州电力设计院有限公司 | Network information security risk assessment system and method thereof |
CN115470962A (en) * | 2022-08-03 | 2022-12-13 | 浙江鸿程计算机系统有限公司 | LightGBM-based enterprise confidence loss risk prediction model construction method |
CN116777213A (en) * | 2023-06-21 | 2023-09-19 | 湖南工商大学 | Carbon transaction market risk early warning system and method based on big data |
CN116842527A (en) * | 2023-07-13 | 2023-10-03 | 陕西财经职业技术学院 | Data security risk assessment method |
CN116882735A (en) * | 2023-06-28 | 2023-10-13 | 刘汉波 | Chemical risk correction early warning method based on process safety index |
CN116911994A (en) * | 2023-07-21 | 2023-10-20 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | External trade risk early warning system |
CN117216801A (en) * | 2023-11-07 | 2023-12-12 | 江苏航运职业技术学院 | Enterprise financial data safety management system and method based on artificial intelligence |
-
2023
- 2023-12-22 CN CN202311774118.5A patent/CN117455245A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529327A (en) * | 2020-12-21 | 2021-03-19 | 北京建筑大学 | Method for constructing fire risk prediction grade model of buildings in commercial areas |
CN113159615A (en) * | 2021-05-10 | 2021-07-23 | 麦荣章 | Intelligent information security risk measuring system and method for industrial control system |
CN114499956A (en) * | 2021-12-24 | 2022-05-13 | 广州电力设计院有限公司 | Network information security risk assessment system and method thereof |
CN115470962A (en) * | 2022-08-03 | 2022-12-13 | 浙江鸿程计算机系统有限公司 | LightGBM-based enterprise confidence loss risk prediction model construction method |
CN116777213A (en) * | 2023-06-21 | 2023-09-19 | 湖南工商大学 | Carbon transaction market risk early warning system and method based on big data |
CN116882735A (en) * | 2023-06-28 | 2023-10-13 | 刘汉波 | Chemical risk correction early warning method based on process safety index |
CN116842527A (en) * | 2023-07-13 | 2023-10-03 | 陕西财经职业技术学院 | Data security risk assessment method |
CN116911994A (en) * | 2023-07-21 | 2023-10-20 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | External trade risk early warning system |
CN117216801A (en) * | 2023-11-07 | 2023-12-12 | 江苏航运职业技术学院 | Enterprise financial data safety management system and method based on artificial intelligence |
Non-Patent Citations (2)
Title |
---|
余培;刘其辉;石城;: "新电改背景下电力用户信用风险预警模型与评价方法", 电力需求侧管理, no. 02, 31 March 2020 (2020-03-31), pages 34 - 38 * |
周元哲: "《Python数据分析与机器学习》", vol. 1, 30 June 2022, 机械工业出版社, pages: 160 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118014373A (en) * | 2024-04-08 | 2024-05-10 | 中国汽车技术研究中心有限公司 | Risk identification model based on data quality monitoring and construction method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110263846B (en) | Fault diagnosis method based on fault data deep mining and learning | |
CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
CN117455245A (en) | Intelligent risk assessment system for enterprise safety production | |
CN108268893B (en) | Chemical industry park early warning method and device based on machine learning | |
CN112660745B (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
CN117095506B (en) | Fire safety monitoring system and method based on alarm area model | |
CN114563150A (en) | Bridge health online detection module generation method, detection method, tool box and device | |
CN115876258A (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
CN116342895B (en) | Method and system for improving sorting efficiency of renewable resources based on AI (advanced technology attachment) processing | |
CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
CN112990656A (en) | Health evaluation system and health evaluation method for IT equipment monitoring data | |
CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
CN114244866A (en) | Production equipment supervisory systems based on thing networking | |
CN114417981B (en) | Intelligent river length inspection system | |
CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
CN117150298B (en) | Deep learning-based subway FAS fire alarm system debugging method | |
CN111667391A (en) | Environment-friendly big data monitoring system | |
CN116845863A (en) | Terminal power grid abnormal equipment access alarm method and device based on space-time track | |
CN111882135B (en) | Internet of things equipment intrusion detection method and related device | |
CN117113259B (en) | Coal mine state data processing method and system for predicting potential safety hazards | |
Doboszewski et al. | Data driven detection of railway point machines failures | |
CN110956340A (en) | Engineering test detection data management early warning decision method | |
CN117688464B (en) | Hidden danger analysis method and system based on multi-source sensor data | |
CN117217625B (en) | Enterprise safety supervision method and device based on data analysis |
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 |