Risk control meeting comprehensive decision and voting system based on big data analysis

Abstract

The invention relates to the technical field of risk decision, and discloses a risk control meeting comprehensive decision and voting system based on big data analysis. The system allows a user to input risk information and automatically identify risks for risk classification through the risk automatic identification module, after the risk analysis module identifies the risks, qualitative and quantitative analysis of the risks is carried out, the severity of the risks is assessed, and the risk priority is determined, and the decision support module applies a decision tree and a simulation mode. The decision tree represents a decision in a graphical mode, a simulation mode is used for simulating results of different decision paths, the data statistics and analysis module automatically counts and analyzes risk points of a project by using a big data technology, provides data support for voting, and provides a decision-making result through automatic risk identification, risk severity analysis and decision-making support. And data support is provided for final voting by using a data statistics and analysis technology, so that the efficiency and accuracy of risk management can be improved, the interference of human factors is reduced, and a more scientific and systematic decision basis is provided for a decision maker.

Description

Technical Field

[0001] The present invention relates to the technical field of risk decision-making, and in particular to a risk control meeting comprehensive decision-making and voting system based on big data analysis. Background Art

[0002] Risk is usually defined as the impact of uncertainty on objectives, especially the potential negative impact on projects, investments or business operations. Risk can come from a variety of factors, including market fluctuations, technical failures, changes in laws and regulations, and natural disasters. The occurrence of risks may lead to financial losses, time delays or waste of resources. Risk management is the process of identifying, assessing and prioritizing risks, aiming to reduce potential losses and maximize opportunities. By identifying and controlling risks, companies can protect their assets and resources and avoid major losses. At the same time, risk management provides more comprehensive information, enabling decision makers to make more informed choices. By identifying and managing risks, companies can better plan for the future and ensure long-term sustainable development.

[0003] Currently, risk control management often involves subjective judgment, resulting in inconsistent opinions among different stakeholders. In addition, due to excessive interference from human factors, the efficiency and accuracy of risk management are reduced. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a risk control comprehensive decision-making and voting system based on big data analysis, which allows users to input risk information through a risk automatic identification module, automatically identifies risks according to built-in rules, and classifies risks. After identifying the risks, the risk analysis module will conduct qualitative and quantitative analysis of the risks, assess the severity of the risks, and determine the risk priority. The decision support module applies a decision tree and a simulation method to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical manner, and the simulation method is used to simulate the results of different decision paths. The data statistics and analysis module uses big data technology to automatically statistically analyze the risk points of the project and provide data support for voting. By automatically identifying risks, analyzing the severity of risks, and providing decision support, and using data statistics and analysis technology to provide data support for the final vote, the efficiency and accuracy of risk management can be improved, the interference of human factors can be reduced, and a more scientific and systematic decision-making basis can be provided for decision makers, etc., thereby solving the above problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a risk control meeting comprehensive decision-making and voting system based on big data analysis, including a risk automatic identification module, a risk analysis module, a decision support module and a data statistics and analysis module;

[0008] The automatic risk identification module allows users to input risk information, automatically identifies risks according to built-in rules, classifies risks, and calculates the user input frequency Srpl;

[0009] After identifying the risk, the risk analysis module will conduct qualitative and quantitative analysis of the risk, assess the severity of the risk, determine the risk priority, and calculate the risk severity score Fxpf;

[0010] The decision support module uses a decision tree and a simulation method to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical way. The simulation method is used to simulate the results of different decision paths and calculate the number of decision paths Jclj, the expected result evaluation yjpg and the number of decision tree nodes Jdsl;

[0011] The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project, and calculates the data analysis report generation frequency Scpl and the risk point occurrence frequency Fdpl to provide data support for voting.

[0012] Preferably, the automatic risk identification module allows the user to input risk information, and understands the risk description input by the user by applying natural language processing (NLP) technology.

[0013] Preferably, the automatic risk identification module allows the user to input risk information and identifies and classifies the risk information by applying a machine learning model.

[0014] Preferably, the automatic risk identification module allows the user to input risk information, automatically identifies risks according to built-in rules, classifies risks, and calculates the user input frequency Srpl. The calculation formula is as follows:

[0015]

[0016] In the formula, Srpl represents the user input frequency, Fxsr i represents the number of inputs of the ith risk type in the time window, w i represents the weight associated with the ith risk type, which is set according to the severity of the risk. Sjck represents the time window, i.e., the total time in the defined time period. Hyyj represents the number of active users, i.e., the number of users who have entered risk information at least once in the time window.

[0017] Preferably, after identifying the risk, the risk analysis module will perform qualitative and quantitative analysis of the risk, assess the severity of the risk, determine the risk priority, and calculate the risk severity score Fxpf, the calculation formula is as follows:

[0018] Fxpf=Yxcd*Fsgl*Kjcx

[0019] In the formula, Fxpf represents the risk severity score, Yxcd represents the potential impact on the project and organization when the risk occurs, Fsgl represents the probability of risk occurrence, and Kjcx represents the difficulty of identifying and detecting the risk before it occurs.

[0020] Preferably, the decision support module applies a decision tree and a simulation method to calculate the number of decision paths Jclj, and the calculation formula is as follows:

[0021]

[0022] In the formula, Jclj represents the number of decision paths, p represents the number of layers of the decision tree, and Dx h Represents the number of decision options at the hth level.

[0023] Preferably, the decision support module uses a decision tree and a simulation method to perform an expected result evaluation Yjpg, and the evaluation formula is as follows:

[0024]

[0025] In the formula, Yjpg represents the expected result, m represents the number of all the results that occur, and Pf j represents the probability of the jth result occurring, Rc j Represents the gain and loss of the jth outcome.

[0026] Preferably, the decision support module applies a decision tree and a simulation method to calculate the number of decision tree nodes Jdsl, and the calculation formula is as follows:

[0027]

[0028] In the formula, Jdsl represents the number of decision tree nodes, p represents the number of layers of the decision tree, and Dx h Represents the number of decision options at the hth level.

[0029] Preferably, the data statistics and analysis module uses big data technology to automatically count and analyze the risk points of the project and calculate the data analysis report generation frequency Scpl. The calculation formula is as follows:

[0030]

[0031] In the formula, Scpl represents the frequency of data analysis report generation, Bgsl represents the number of reports generated in the time period, and T represents the total time of the time period.

[0032] Preferably, the data statistics and analysis module uses big data technology to automatically analyze the risk points of the project and calculate the frequency of occurrence of risk points Fdpl. The calculation formula is as follows:

[0033]

[0034] In the formula, Fdpl represents the frequency of occurrence of risk points, Fxsl represents the number of risk points occurring in the time period, and T represents the total time of the time period.

[0035] Compared with the prior art, the present invention provides a risk control meeting comprehensive decision-making and voting system based on big data analysis, which has the following beneficial effects:

[0036] The present invention allows users to input risk information through the risk automatic identification module, automatically identifies risks according to built-in rules, and classifies risks. After identifying the risks, the risk analysis module will perform qualitative and quantitative analysis of the risks, evaluate the severity of the risks, and determine the risk priority. The decision support module uses decision trees and simulation methods to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical manner, and the simulation method is used to simulate the results of different decision paths. The data statistics and analysis module uses big data technology to automatically statistically analyze the risk points of the project and provide data support for voting. By automatically identifying risks, analyzing the severity of risks, and providing decision support, and using data statistics and analysis technology to provide data support for the final vote, the efficiency and accuracy of risk management can be improved, the interference of human factors can be reduced, and a more scientific and systematic decision-making basis can be provided for decision makers. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the system flow of the present invention.

[0038] Figure 2 The figure is a schematic diagram of the steps of using the system of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In view of the fact that risk control management currently involves subjective judgment, resulting in inconsistent opinions among different stakeholders, and excessive interference from human factors, which reduces the efficiency and accuracy of risk management, a risk control meeting comprehensive decision-making and voting system based on big data analysis is proposed. Figure 1 ,The system includes a risk automatic identification module, a risk analysis module, a decision support module, and a data statistics and analysis module;

[0041] The risk automatic identification module uses natural language processing (NLP) technology to understand the risk descriptions input by users, cleans and preprocesses the risk descriptions input by users, including removing stop words, punctuation marks and performing word form restoration to ensure the consistency of input data, and uses NER technology to identify key entities in the input text, such as specific projects, risk types, time, location, etc., which helps to extract more informative features. At the same time, sentiment analysis technology is applied to evaluate the emotional tendency of user input to help identify the risk severity level that may exist in the description, and machine learning models are applied to identify and classify risk information. The classification model is trained through deep learning neural networks to learn from historical risk data and automatically identify new risk types. Clustering algorithms are applied to analyze unlabeled data to find potential risk patterns and trends as well as similarities, where the user input frequency is calculated, expressed as follows:

[0042]

[0043] By monitoring the frequency of user input, the system can quickly identify frequently occurring risk descriptions or issues. This timeliness helps take preventive measures before the risk becomes serious. In the formula, Srpl represents the user input frequency, and Fxsr represents the user input frequency. i represents the number of inputs of the ith risk type in the time window, w i represents the weight associated with the ith risk type, which is set according to the severity of the risk. Sjck represents the time window, i.e., the total time within the defined time period. Hyyh represents the number of active users, i.e., the number of users who have entered risk information at least once within the time window. At the same time, the user input frequency can be used as an important indicator of risk priority. Frequently appearing risk information may indicate that it has a wide impact or great potential harm, thus helping decision makers to prioritize these risks.

[0044] After identifying the risk, the risk analysis module will conduct qualitative and quantitative analysis of the risk, use descriptive statistical analysis to analyze historical data, understand the distribution characteristics of the risk, apply the Bayesian network model to quantify the possibility of the risk, and combine the probability and impact to calculate the risk value. The formula is: risk value = probability of occurrence × potential impact. This value is used to quantify and compare different risks. According to the risk value and qualitative analysis results, the weighted scoring method is used to prioritize the risks, determine the risks that should be given priority, and calculate the risk severity score Fxpf. The calculation formula is as follows:

[0045] Fxpf=Yxcd*Fsgl*Kjcx

[0046] By quantifying the risk severity score, the decision-making process is based on data and models rather than subjective judgment, which reduces the decision-making bias. In the formula, Fxpf represents the risk severity score, Yxcd represents the potential impact on the project and organization when the risk occurs, Fsgl represents the probability of risk occurrence, and Kjcx represents the difficulty of identifying and detecting the risk before it occurs. At the same time, through the score calculation under different scenarios, it helps the management understand the changes in risks under different circumstances and formulate corresponding response strategies;

[0047] The decision support module uses decision trees and simulation methods to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical way. The simulation method is used to simulate the results of different decision paths and calculate the number of decision paths Jclj, the expected result evaluation Yjpg and the number of decision tree nodes Jdsl, where:

[0048] The formula for calculating the number of decision paths is as follows:

[0049]

[0050] By calculating different decision paths, the decision-making process can be clearly displayed to help participants understand the consequences of each choice. Each decision path can be recorded and traced to ensure the transparency of the decision-making process and facilitate subsequent audits and evaluations. In the formula, Jclj represents the number of decision paths, p represents the number of layers of the decision tree, and Dx represents the number of decision paths. h Indicates the number of decision options at the hth level. By showing the risk results of different decision paths, it can enhance the risk awareness of team members and improve the overall risk management capabilities.

[0051] The expected result evaluation formula is as follows:

[0052]

[0053] By evaluating the expected results, decision makers can make more scientific decisions based on data and analysis, reducing the impact of subjective judgment. In the formula, Yjpg represents the expected result, m represents the number of all possible results, and Pf j represents the probability of the jth result occurring, Rc j Indicates the gains and losses of the jth result. By clarifying the expected results, all participants can better understand the purpose and expected effects of the decision, and enhance the transparency of the decision-making process.

[0054] The formula for calculating the number of decision tree nodes is as follows:

[0055]

[0056] By calculating the number of nodes in the decision tree, decision makers can more clearly understand the complexity of the decision process and identify key decision points. In the formula, Jdsl represents the number of nodes in the decision tree, p represents the number of layers in the decision tree, and Dx h Indicates the number of decision options at the hth level. The calculation of the number of nodes helps to simplify decision analysis and facilitate team members to quickly grasp the decision structure;

[0057] The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project, analyzes historical risk data through the time series model ARIMA, predicts future risk trends and patterns, and uses the linear regression model to evaluate the impact of different factors on risks, helping decision makers understand the driving factors of risks, and calculates the data analysis report generation frequency Scpl and the risk point occurrence frequency Fdpl to provide data support for voting, including:

[0058] The calculation formula for the frequency of data analysis report generation is as follows:

[0059]

[0060] By regularly generating data analysis reports, potential risk points can be quickly identified, ensuring that decision makers can take timely measures to reduce the possibility of risk. In the formula, Scpl represents the frequency of data analysis report generation, Bgsl represents the number of reports generated in a time period, and T represents the total time of the time period. Frequent report generation enables decision makers to dynamically adjust risk management strategies based on the latest data, enhancing the flexibility and adaptability of the system.

[0061] The formula for calculating the frequency of risk points is as follows:

[0062]

[0063] By calculating the frequency of occurrence of risk points, potential risks can be identified in a timely manner, helping decision makers take measures before the problem expands. In the formula, Fdpl represents the frequency of occurrence of risk points, Fxsl represents the number of risk points that occur in a time period, and T represents the total time of the time period. Frequency data provides a quantitative assessment of risks, allowing decision makers to more clearly understand the severity and scope of risks.

[0064] The data statistics and analysis module uses Tableau to display real-time risk data and analysis results by building interactive dashboards, helping decision makers quickly obtain key information. It also uses charts, heat maps, and scatter plot visualization tools to intuitively display risk patterns and trends and enhance the comprehensibility of data.

[0065] By automatically identifying risks, analyzing risk severity, and providing decision support, and using data statistics and analysis techniques to provide data support for the final vote, the efficiency and accuracy of risk management can be improved, the interference of human factors can be reduced, and a more scientific and systematic basis for decision makers can be provided.

[0066] See also Figure 2 , a method for using a risk control meeting comprehensive decision-making and voting system based on big data analysis, comprising the following steps:

[0067] S1. The user inputs risk information into the risk automatic identification module. The module automatically identifies risks according to built-in rules, classifies risks, and calculates the user input frequency Srpl;

[0068] S2. After identifying the risk, the risk analysis module will conduct qualitative and quantitative analysis of the risk, assess the severity of the risk, determine the risk priority, and calculate the risk severity score Fxpf;

[0069] S3, the decision support module uses decision trees and simulation methods to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical way. The simulation method is used to simulate the results of different decision paths and calculate the number of decision paths Jclj, the expected result evaluation Yjpg and the number of decision tree nodes Jdsl;

[0070] S4. The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project and calculate the data analysis report generation frequency Scpl and the risk point occurrence frequency Fdpl to provide data support for voting.

[0071] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive decision-making and voting system for risk control meetings based on big data analysis, characterized by: It includes automatic risk identification module, risk analysis module, decision support module and data statistics and analysis module; The automatic risk identification module allows users to input risk information, automatically identifies risks according to built-in rules, classifies risks, and calculates the user input frequency Srpl; After identifying the risk, the risk analysis module will conduct qualitative and quantitative analysis of the risk, assess the severity of the risk, determine the risk priority, and calculate the risk severity score Fxpf; The decision support module uses a decision tree and a simulation method to make decisions based on the above risk analysis results. The decision tree represents the decision in a graphical way. The simulation method is used to simulate the results of different decision paths and calculate the number of decision paths Jclj, the expected result evaluation Yjpg and the number of decision tree nodes Jdsl; The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project, and calculates the data analysis report generation frequency Scpl and the risk point occurrence frequency Fdpl to provide data support for voting.

2. According to claim 1, a risk control meeting comprehensive decision-making and voting system based on big data analysis is characterized by: The automatic risk identification module allows the user to input risk information and understands the risk description input by the user by applying natural language processing (NLP) technology.

3. According to claim 2, a risk control meeting comprehensive decision-making and voting system based on big data analysis is characterized by: The automatic risk identification module allows users to input risk information and identifies and classifies the risk information by applying a machine learning model.

4. According to claim 3, a risk control meeting comprehensive decision-making and voting system based on big data analysis is characterized by: The automatic risk identification module allows users to input risk information, automatically identifies risks according to built-in rules, classifies risks, and calculates the user input frequency Srpl. The calculation formula is as follows: In the formula, Srpl represents the user input frequency, Fxsr i represents the number of inputs of the ith risk type in the time window, w i represents the weight associated with the i-th risk type, which is set according to the severity of the risk. Sjck represents the time window, that is, the total time in the defined time period. Hyyh represents the number of active users, that is, the number of users who have entered risk information at least once in the time window.

5. According to claim 4, a risk control meeting comprehensive decision-making and voting system based on big data analysis is characterized by: After identifying the risk, the risk analysis module will conduct qualitative and quantitative analysis of the risk, assess the severity of the risk, determine the risk priority, and calculate the risk severity score Fxpf. The calculation formula is as follows: Fxpf=Yxcd*Fsgl*Kjcx In the formula, Fxpf represents the risk severity score, Yxcd represents the potential impact on the project and organization when the risk occurs, Fsgl represents the probability of risk occurrence, and Kjcx represents the difficulty of identifying and detecting the risk before it occurs.

6. The risk control meeting comprehensive decision-making and voting system based on big data analysis according to claim 5 is characterized by: The decision support module uses decision trees and simulation methods to calculate the number of decision paths Jclj. The calculation formula is as follows: In the formula, Jclj represents the number of decision paths, p represents the number of layers of the decision tree, and Dx h Represents the number of decision options at the hth level.

7. The risk control meeting comprehensive decision-making and voting system based on big data analysis according to claim 6 is characterized by: The decision support module uses decision trees and simulation methods to evaluate the expected results Yjpg. The evaluation formula is as follows: In the formula, Yjpg represents the expected result, m represents the number of all the results that occur, and Pf j represents the probability of the jth result occurring, Rc j Represents the gain and loss of the jth outcome.

8. The risk control meeting comprehensive decision-making and voting system based on big data analysis according to claim 7 is characterized by: The decision support module uses a decision tree and a simulation method to calculate the number of decision tree nodes Jdsl, and the calculation formula is as follows: In the formula, Jdsl represents the number of decision tree nodes, p represents the number of layers of the decision tree, and Dx h Represents the number of decision options at the hth level.

9. The risk control meeting comprehensive decision-making and voting system based on big data analysis according to claim 8 is characterized by: The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project and calculate the frequency of generating data analysis reports Scpl. The calculation formula is as follows: In the formula, Scpl represents the frequency of data analysis report generation, Bgsl represents the number of reports generated in the time period, and T represents the total time of the time period.

10. The risk control meeting comprehensive decision-making and voting system based on big data analysis according to claim 9 is characterized by: The data statistics and analysis module uses big data technology to automatically analyze the risk points of the project and calculate the frequency of occurrence of risk points Fdpl. The calculation formula is as follows: In the formula, Fdpl represents the frequency of occurrence of risk points, Fxsl represents the number of risk points occurring in the time period, and T represents the total time of the time period.

Images