Personal risk assessment method and device and computer equipment

Abstract

The invention relates to a personal risk assessment method and device and computer equipment, and the method comprises the steps: obtaining the risk data of a target person, inputting the risk data into a multi-dimensional analysis model which is based on a plurality of assessment dimensions and is used for the quantitative assessment of the core indexes of the personal risk degree of the target person, and carrying out the risk assessment processing; and obtaining a risk assessment result of the target person. According to the method, the personal risk degree of the target personnel can be accurately and quantitatively evaluated in multiple aspects by determining the core indexes, and the evaluation efficiency can be improved by establishing the multi-dimensional analysis model through the core indexes.

Description

Technical Field

[0001] The present application relates to the technical field of risk identification, and in particular to a personal risk assessment method, device and computer equipment. Background Art

[0002] At present, various types of accident hazards and safety risks are intertwined in power production, personal safety accidents in production operations are prone to occur frequently, and the situation of personal safety risk management remains severe.

[0003] At present, personal risk assessment is usually based on experience-based judgment. At the same time, the large amount of data generated by historical accidents, violations, personnel management, environment and other operational risk management processes lacks systematic and effective management and application. The assessment results cannot accurately reflect the personal risks of production personnel. Summary of the invention

[0004] Based on this, it is necessary to provide a personal risk assessment method, device and computer equipment that can accurately reflect the personal risks of production personnel in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a personal risk assessment method, the method comprising:

[0006] Obtain risk data of target personnel;

[0007] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0008] In one embodiment, the multidimensional analysis model includes multiple risk assessment models, and the risk assessment models correspond to the core indicators one by one; the risk data is input into the pre-established multidimensional analysis model for risk assessment processing, and the risk assessment results of the target personnel are obtained, including:

[0009] Get the weights corresponding to each core indicator;

[0010] Input the risk data into the corresponding risk assessment model for risk assessment processing and determine the indicator values ​​corresponding to each core indicator;

[0011] Determine the risk assessment results of the target personnel based on the weights and indicator values ​​corresponding to each core indicator.

[0012] In one embodiment, the risk assessment result of the target person is determined according to the weights and indicator values ​​corresponding to the core indicators, including:

[0013] Add the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value;

[0014] Determine the risk assessment results of the target personnel based on the total indicator value and the preset indicator threshold.

[0015] In one embodiment, the process of determining the core indicators includes:

[0016] Obtain target generalized information data;

[0017] The target generalized information data is input into the clustering model for clustering analysis to obtain the core indicators.

[0018] In one embodiment, the target generalized information data includes multiple data points; the target generalized information data is input into a clustering model for clustering analysis to obtain core indicators, including:

[0019] Each data point is input into the clustering model for random selection to determine multiple initial cluster centers;

[0020] Calculate the distance between each data point and each initial cluster center to obtain multiple distance results;

[0021] According to the distance results, each data point is classified into the corresponding initial cluster center to obtain the classification result;

[0022] Determine the core indicators based on the classification results.

[0023] In one embodiment, the above-mentioned obtaining of target generalized information data includes:

[0024] Acquire initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data;

[0025] The equipment index data, environmental index data and personnel status index data are respectively cleaned, integrated and converted to obtain the target generalized information data.

[0026] In one embodiment, the method comprises:

[0027] The risk assessment results of the target personnel are input into the feature extraction model for prediction processing to obtain the prediction results;

[0028] When the prediction results meet the warning conditions, the warning information is output.

[0029] In one embodiment, the risk assessment result includes a risk assessment text; the risk assessment result of the target person is input into a feature extraction model for prediction processing, and the prediction result obtained includes:

[0030] Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features;

[0031] Perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text;

[0032] The predicted text corresponding to the maximum probability is determined as the prediction result.

[0033] In a second aspect, the present application further provides a personal risk assessment device, the device comprising:

[0034] A data acquisition module is used to obtain risk data of target personnel;

[0035] The result determination module is used to input risk data into a pre-established multi-dimensional analysis model for risk assessment processing to obtain risk assessment results for target personnel; wherein the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0036] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0037] Obtain risk data of target personnel;

[0038] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain risk data of target personnel;

[0041] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0042] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtain risk data of target personnel;

[0044] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0045] The above-mentioned personal risk assessment method, device and computer equipment obtain the risk data of the target person, input the risk data into a multidimensional analysis model constructed based on multiple assessment dimensions for quantitatively assessing the personal risk level of the target person, and obtain the risk assessment result of the target person. The present application can accurately assess the personal risk level of the target person in multiple aspects by determining the core indicators, and the evaluation efficiency can be improved by establishing a multidimensional analysis model through the core indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A diagram of an application environment of a personal risk assessment method in one embodiment;

[0047] Figure 2 A schematic diagram of a process of a personal risk assessment method in one embodiment;

[0048] Figure 3 A linear fitting schematic diagram in one embodiment;

[0049] Figure 4 A schematic diagram of a process for determining a risk assessment result of a target person in one embodiment;

[0050] Figure 5 A schematic diagram of a process for determining a risk assessment result of a target person in another embodiment;

[0051] Figure 6 Schematic diagram of a process for determining a core indicator in an embodiment;

[0052] Figure 7 A schematic diagram of a process for obtaining core indicators in an embodiment;

[0053] Figure 8 A schematic diagram of a process for obtaining target generalized information data in one embodiment;

[0054] Fig. 9 A schematic diagram of a process of a personal risk assessment method in another embodiment;

[0055] Fig.10 A schematic diagram of a process for obtaining a prediction result in one embodiment;

[0056] Fig.11 is a structural block diagram of a personal risk assessment device in one embodiment;

[0057] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] First of all, before specifically introducing the technical solution of the embodiments of the present application, the technical background based on the embodiments of the present application is introduced.

[0060] The safety management of power supply enterprises mainly involves two aspects, including personal safety and power supply safety. Personal safety refers to the safety of power supply enterprise personnel during work, and power supply safety refers to the equipment safety of power supply enterprises and ensuring the stability of power supply. These two aspects of safety are also interrelated.

[0061] By analyzing the data of power supply enterprises and data related to power supply, it can serve as a reference and auxiliary for the safety management of power supply enterprises. For example, the related technology discloses an intelligent management system for power systems, including a power generation management module, a distribution automation safety platform, a power quality module, a dispatching management module, an energy-saving management module, a power consumption service module, a power grid line inspection module, and a weather forecast module. It can realize intelligent auxiliary support for operation management decisions in a more intelligent way, improve the safety and stability of the operation of the smart grid system, and provide efficient and accurate weather forecast services to ensure the safe operation of the power grid lines. Another related technology discloses a method and system for disaster prevention and early warning and production decision support for distribution networks, which can integrate multiple types of data from data centers, classify, analyze, and extract features from multiple source data of distribution networks, and then evaluate the risk of power outages in distribution networks and perform risk grading by calculating the maximum wind load, lightning trip rate, maximum current carrying capacity at the highest allowable operating temperature, and the average failure frequency and average failure time considering environmental factors without the need to install additional meteorological environment monitoring devices.

[0062] The dynamic analysis technology of personal risk based on generalized information can be traced back to the end of the 20th century. At that time, with the rapid development of information technology, people began to realize the importance of information for risk management. In this context, researchers began to explore how to use information technology to improve the efficiency and accuracy of personal risk management. In early research, people mainly focused on how to use computer technology to process and analyze a large amount of risk data. For example, researchers developed various risk assessment and prediction models, using computer programs to automatically calculate and analyze risk data, and generate risk reports and early warning information. These early studies mainly focused on data processing and analysis without considering the nature and generality of information. However, with the rapid development of information technology and data science, people began to realize that information is not only a form of data, but also a valuable resource. In this context, researchers began to explore how to study the dynamic analysis technology of personal risk from the perspective of generalized information. The dynamic analysis technology of personal risk based on generalized information not only focuses on data processing and analysis, but also focuses on how to extract useful information from a large amount of risk data.

[0063] Based on this, the present application provides a personal risk assessment method, device and computer equipment, aiming to solve the above technical problems.

[0064] The personal risk assessment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 obtains the risk data of the target person, inputs the risk data into a multidimensional analysis model based on multiple assessment dimensions to construct core indicators for quantitatively assessing the degree of personal risk of the target person, and performs risk assessment processing to obtain the risk assessment result of the target person. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0065] In an exemplary embodiment, Figure 2 As shown, the present application provides a personal risk assessment method, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, including the following S201 to S202. Among them:

[0066] S201, obtaining risk data of target personnel.

[0067] Among them, target personnel may include personnel of power supply companies; risk data may include the number of violations, the number of safety accidents, etc.

[0068] In an embodiment of the present application, the risk data of the target person can be stored in a system database, and the terminal obtains the risk data by accessing the system database. The risk data of the target person can also be input by a staff member, and the terminal can obtain the risk data input by the staff member.

[0069] S202, input the risk data into a pre-established multi-dimensional analysis model for risk assessment processing to obtain a risk assessment result for the target person.

[0070] The multi-dimensional analysis model is constructed based on the core indicators of multiple evaluation dimensions, which are used to quantitatively evaluate the degree of personal risk of the target person. The risk assessment results are used to characterize the degree of personal risk of the target person.

[0071] In the establishment of the multidimensional analysis model in the embodiment of the present application, it is necessary to consider indicators of multiple dimensions, such as equipment safety, working environment, employee health status, safety management and other indicators. The indicators of each dimension can include corresponding risk factors and evaluation indicator data for quantitatively evaluating the size of personal risks. Before the embodiment of the present application, it is necessary to build a multidimensional analysis model. After the construction is completed, the model needs to be trained. The embodiment of the present application can use the linear regression model in the supervised learning model category for data training, combined with Figure 3 As shown, the linear regression model is a mathematical regression model used to describe the relationship between two or more variables. In a univariate linear regression model, there is one independent variable and one dependent variable, while in a multiple linear regression model, there are multiple independent variables and one dependent variable. In a linear regression model, the dependent variable is a random variable, and the independent variable is a non-random variable. The regression coefficient in the model is used to describe the degree of influence of the independent variable on the dependent variable, while the random error term represents other influencing factors other than the independent variable. In a univariate linear regression model, if there is one independent variable and one dependent variable, it can be expressed as y=ax+b, where a is the regression coefficient and b is the intercept. In a multiple linear regression model, if there are multiple independent variables and one dependent variable, it can be expressed as y=a1x1+a2x2+...+anxn+b, where an is the regression coefficient of each independent variable and b is the intercept. It should be noted that the application of the linear regression model has certain limitations. In practical applications, it is necessary to ensure that the data conforms to a linear relationship, and it is necessary to consider whether there are problems such as multicollinearity. When performing linear regression analysis, it is also necessary to pay attention to issues such as the hypothesis test of the model and the goodness of fit of the model.

[0072] In the embodiment of the present application, the risk data is input into a multidimensional analysis model, which can calculate the value of each indicator and compare the total value with a preset threshold to obtain the risk assessment result of the target person. The risk assessment result of the target person can also be determined based on the value of each indicator and a pre-built calculation sub-model.

[0073] The above-mentioned personal risk assessment method obtains the risk data of the target person, inputs the risk data into a multidimensional analysis model constructed based on multiple assessment dimensions for quantitatively assessing the personal risk level of the target person, and performs risk assessment processing to obtain the risk assessment result of the target person. This application can accurately assess the personal risk level of the target person in multiple aspects by determining the core indicators, and the evaluation efficiency can be improved by establishing a multidimensional analysis model through the core indicators.

[0074] In an exemplary embodiment, based on the above embodiment, see Figure 4 The multidimensional analysis model of the embodiment of the present application includes multiple risk assessment models, and the risk assessment models correspond to the core indicators one by one; the embodiment of the present application involves the process of inputting risk data into a pre-established multidimensional analysis model for risk assessment processing to obtain the risk assessment result of the target person, including the following S301 to S303. Among them:

[0075] S301, obtaining the weight corresponding to each core indicator.

[0076] The weights of the embodiments of the present application can be input by a staff member, or obtained by optimizing the model during training.

[0077] S302, input the risk data into the corresponding risk assessment model for risk assessment processing, and determine the indicator value corresponding to each core indicator.

[0078] The embodiment of the present application inputs the risk data into the corresponding risk assessment model in the multi-dimensional analysis model. The risk assessment model can calculate the value of each indicator and finally determine the indicator value corresponding to each core indicator.

[0079] S303, determining the risk assessment result of the target person according to the weight and indicator value corresponding to each core indicator.

[0080] In the embodiment of the present application, the risk assessment result of the target person is obtained by comparing the total value with the preset threshold value. The risk assessment result of the target person can also be determined according to the value of each indicator and the pre-built calculation sub-model.

[0081] In an embodiment of the present application, a multidimensional analysis model is established for analyzing the systemic personal risks of power supply enterprises. The multidimensional analysis model establishes indicators of multiple dimensions, including indicators of equipment safety, working environment, employee health status, and safety management. The indicators of each dimension contain corresponding risk factors and evaluation indicator data, and the weights and interrelationships of the indicators of each dimension are determined, so that potential personal risks can be identified quickly and accurately.

[0082] In an exemplary embodiment, based on the above embodiment, see Figure 5 The embodiment of the present application relates to a process of determining the risk assessment result of a target person according to the weights and indicator values ​​corresponding to each core indicator, including the following S401 to S402. Among them:

[0083] S401, adding up the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value.

[0084] In the embodiment of the present application, based on the weights corresponding to the core indicators obtained in the above embodiment, the terminal adds the product of the weights corresponding to the core indicators and the indicator value to obtain the total indicator value, which can be expressed as a1*w1+a2*w2+a3*w3+a4*w4.

[0085] S402: Determine the risk assessment result of the target person according to the total indicator value and the preset indicator threshold.

[0086] In the embodiment of the present application, based on the total index value obtained in the above embodiment, the terminal can compare the total index value with a preset index threshold, wherein the preset index threshold may include multiple thresholds corresponding to different risk levels. For example, if the total index value is 50, and the index threshold indicating a medium risk level is 40, then the risk assessment result is that there is a medium risk.

[0087] In an exemplary embodiment, based on the above embodiment, see Figure 6 The process of determining the core indicators of the embodiment of the present application includes the following S501 to S502. Among them:

[0088] S501, obtaining target generalized information data.

[0089] The target generalized information data refers to the generalized information data after data processing.

[0090] In an embodiment of the present application, the target generalized information data may be stored in a system database, and the terminal obtains the target generalized information data by accessing the system database. The target generalized information data may also be input by a staff member, and the terminal may obtain the target generalized information data input by the staff member.

[0091] S502, inputting the target generalized information data into the clustering model for clustering analysis and processing to obtain core indicators.

[0092] In the embodiments of the present application, the clustering model may adopt K-means clustering and K-medoids clustering. K-means clustering distributes data points into K clusters through iterative optimization, and each cluster is defined by its centroid (mean). The specific process of cluster analysis includes data preprocessing, selecting clustering methods, setting parameters, performing cluster analysis, and interpreting results.

[0093] The embodiments of the present application utilize a clustering model to adopt data mining and machine learning to automatically extract core indicator data information and dynamically calculate the core indicator values. These core indicators are statistical data, historical experience values ​​or industry standards on personnel work safety. Indicators such as the number of personnel work violations and the incidence rate of safety accidents can be set as an important basis for judging personal risks. By comparing actual data with these core indicators, the personal risks existing in the work of power supply company personnel can be intelligently identified, and based on these factors, possible risks in the future can be predicted, and personal risk avoidance strategies can be intelligently generated, so that power supply company personnel can make precautionary and response preparations in advance to reduce the probability and impact of safety accidents.

[0094] In an exemplary embodiment, based on the above embodiment, see Figure 7 The target generalized information data of the embodiment of the present application includes multiple data points; the embodiment of the present application involves a process of inputting the target generalized information data into a clustering model for clustering analysis and processing to obtain core indicators, including the following S601 to S604. Among them:

[0095] S601, input each data point into the clustering model for random selection processing to determine multiple initial cluster centers.

[0096] In the embodiment of the present application, the clustering algorithm may be a K-means clustering model (K-Means Cluster), which is mainly used to quickly classify other cases into corresponding categories when the number of cluster categories has been determined, and is suitable for clustering of large sample data. The cluster analysis implementation steps mainly adopt mathematical statistics methods, and cluster analysis is a multivariate statistical method for classifying individuals or objects according to the principle of "birds of a feather flock together". Principal component analysis is a statistical method that uses the idea of ​​dimensionality reduction to convert multiple indicators into a few comprehensive indicators while ensuring little information loss. Factor analysis also uses the idea of ​​dimensionality reduction to group the original variables according to the size of the correlation, so that the correlation between variables in each group is high and the correlation between variables in different groups is low.

[0097] S602, calculating the distance between each data point and each initial cluster center to obtain multiple distance results.

[0098] In the embodiment of the present application, K initial cluster centers are randomly initialized, and then the sample points are assigned to the cluster represented by the nearest center point according to the distance from the data point to these initial cluster centers.

[0099] S603, classifying each data point into a corresponding initial cluster center according to the distance result to obtain a classification result.

[0100] In this embodiment of the present application, the center point of each cluster is updated to the average value of all sample points in the cluster, and this process is iterated continuously until the center point no longer changes or the specified number of iterations is reached.

[0101] S604, determine the core indicators based on the classification results.

[0102] In the embodiment of the present application, a clustering algorithm is used to adopt data mining and machine learning to automatically extract core indicator data information and dynamically calculate the core indicator values. The idea of ​​dimensionality reduction is used to convert multiple indicators into a statistical method of a few comprehensive indicators while ensuring little information loss. Factor analysis also uses the idea of ​​dimensionality reduction to group the original variables according to the size of the correlation, so that the correlation between variables in each group is higher and the correlation between variables in different groups is lower.

[0103] The embodiments of the present application can intelligently identify the personal risks existing in the work of power supply enterprise personnel, predict the risks that may arise in the future based on these factors, and intelligently generate personal risk avoidance strategies, so that power supply enterprise personnel can make prevention and response preparations in advance, reducing the probability and impact of safety accidents.

[0104] In an exemplary embodiment, based on the above embodiment, see Figure 8 The embodiment of the present application relates to a process of obtaining target generalized information data, including the following S701 to S702. Among them:

[0105] S701, obtaining initial generalized information data.

[0106] Among them, the initial generalized information data includes equipment index data, environmental index data and personnel status index data.

[0107] In an embodiment of the present application, the terminal can obtain initial generalized information data from various systems of production management, equipment monitoring, employee health management, and safety accident reporting of the power supply enterprise.

[0108] S702, respectively, perform data cleaning, data integration and data conversion processing on the equipment index data, the environmental index data and the personnel status index data in turn to obtain the target generalized information data.

[0109] In an embodiment of the present application, various data from various systems of the power supply enterprise's production management, equipment monitoring, employee health management, and safety accident reporting are obtained, and the acquired data is cleaned and integrated to eliminate erroneous data and outliers to ensure the accuracy and reliability of the data. After the data is cleaned and integrated, the data is converted into a data format that can be used for analysis, and then stored in a personal risk information database.

[0110] Specifically, when establishing a personal risk information database, the architecture and design of the database should be clarified first, including determining the type of data to be collected, the source of data, and the way of data storage. On this basis, a complete data collection mechanism should be established to ensure that data related to personal risks are obtained from various departments and systems of the power supply enterprise. When storing personal risk information of power supply enterprise personnel, various corresponding data are collected from various systems such as production management, equipment monitoring, employee health management, and safety accident reports of the power supply enterprise. These data include power supply data (such as power production, power consumption, etc.), equipment operation data (such as equipment failure times, maintenance records, etc.), employee health files (such as physical examination results, disease records, etc.) and safety accident reports (such as accident causes, treatment results, etc.). Optionally, the technology for obtaining these data mainly adopts two methods: synchronous data real-time capture of database personnel information of employee systems, and offline import of personnel information data. The purpose of data cleaning and integration is to eliminate erroneous data and outliers, and ensure the accuracy and reliability of data. For example, for the number of equipment failures, outliers or erroneous data need to be excluded to avoid negative impact on the analysis results. Data integration is to integrate and unify data from different sources for subsequent analysis and processing. After cleaning and integrating the data, the data needs to be converted to a data format that can be used for analysis. This involves data classification, normalization, and standardization to meet the requirements of the analysis model for the data format. For example, the number of equipment failures may need to be converted into relative values ​​such as failure rate per million hours to facilitate comparison and analysis between different devices. After the processed data is stored in the personal risk information database, the database needs to have efficient data storage and query functions to quickly retrieve and analyze data. At the same time, the database also needs to support data updates and maintenance to update the data in a timely manner and maintain the accuracy and integrity of the data.

[0111] In an exemplary embodiment, based on the above embodiment, see Fig. 9 The method of the embodiment of the present application further includes the following S801 to S802. Among them:

[0112] S801, input the risk assessment result of the target person into the feature extraction model for prediction processing to obtain the prediction result.

[0113] In the embodiment of the present application, by comparing the risk assessment results of the target personnel with these core indicators, the personal risks existing in the work of the power supply enterprise personnel can be intelligently identified, and the risks that may arise in the future can be predicted based on these factors, and personal risk avoidance strategies can be intelligently generated, so that the power supply enterprise personnel can make prevention and response preparations in advance to reduce the probability and impact of safety accidents.

[0114] S802: When the prediction result meets the warning condition, output warning information.

[0115] In the embodiment of the present application, the converted information is stored in a personal risk information database, and then a multidimensional analysis model for analyzing the systemic personal risks of the power supply enterprise is established. The supervised learning model is used to train the multidimensional analysis model. Then, a clustering algorithm is used to extract core indicator data information and dynamically calculate the core indicator values. Then, the personal risk information database is used to receive and store the work information of the power supply enterprise personnel in real time. This information is used as the input of the clustering algorithm to obtain risk warning information. Then, a language model is used to extract the key elements in the risk warning information, so as to quickly and accurately identify potential personal risks. In addition, a real-time monitoring and warning system can be used to perform real-time monitoring and warning, and a warning signal can be automatically issued, which plays a good auxiliary and warning role in the safety management of the power supply enterprise.

[0116] This personal risk dynamic analysis method based on generalized information utilizes the interaction between people and systems to monitor and warn the operating status of power supply enterprises and employee personal risks in real time, help power supply enterprises predict potential safety hazards when power personnel are working, and provide risk avoidance strategies. By using the personal risk dynamic analysis system based on generalized information, the scientificity and effectiveness of personal risk management can be improved, and the safety and competitiveness of enterprises can be enhanced.

[0117] In an exemplary embodiment, based on the above embodiment, see Fig.10 The risk assessment result of the embodiment of the present application includes a risk assessment text; the embodiment of the present application involves inputting the risk assessment result of the target person into the feature extraction model for prediction processing to obtain the prediction result, including the following S901 to S903. Among them:

[0118] S901, input the risk assessment text into a feature extraction model for feature extraction processing to obtain multiple text features.

[0119] In the embodiment of the present application, natural language processing and knowledge graph technology are used to automatically extract key elements in risk warning information through a feature extraction model to quickly and accurately identify potential personal risks. Optionally, the feature extraction model can use an n-gram language model.

[0120] S902, performing prediction processing on each text feature to obtain a plurality of predicted texts and probabilities corresponding to each predicted text.

[0121] The n-gram model is a model based on statistical linguistics. It is used to predict the possibility of the next word or character in a text. The n-gram model is a conditional probability model that predicts the possibility of the next word or character by calculating the probability of n consecutive words or characters in a text sequence. The n-gram language model expression is shown in formula (1):

[0122] (1)

[0123] Among them, P is the probability and W is the weight.

[0124] S903: Determine the predicted text corresponding to the maximum probability as the prediction result.

[0125] In the embodiment of the present application, based on the multiple probabilities obtained in the above embodiment, the predicted text corresponding to the maximum probability is determined as the prediction result.

[0126] In an exemplary embodiment, based on the above embodiment, the method of the embodiment of the present application further includes the following steps:

[0127] Step 1: Obtain initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data; respectively, the equipment index data, environmental index data and personnel status index data are cleaned, integrated and converted to obtain target generalized information data;

[0128] Step 2: Input each data point into the clustering model for random selection and determine multiple initial cluster centers; calculate the distance between each data point and each initial cluster center to obtain multiple distance results; classify each data point to the corresponding initial cluster center according to the distance result to obtain the classification result; determine the core indicator according to the classification result;

[0129] Step 3: Obtain the risk data of the target personnel; obtain the weights corresponding to each core indicator; input the risk data into the corresponding risk assessment model for risk assessment processing, and determine the indicator values ​​corresponding to each core indicator;

[0130] Step 4: Add the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value; determine the risk assessment result of the target person based on the total indicator value and the preset indicator threshold;

[0131] Step 5: Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features; perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text; determine the predicted text corresponding to the maximum probability as the prediction result;

[0132] Step 6: When the prediction results meet the warning conditions, output the warning information.

[0133] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0134] Based on the same inventive concept, the embodiment of the present application also provides a personal risk assessment device for implementing the personal risk assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more personal risk assessment device embodiments provided below can refer to the limitations on the personal risk assessment method above, and will not be repeated here.

[0135] In one embodiment, Fig.11 As shown, a personal risk assessment device 1000 is provided, comprising:

[0136] Data acquisition module 1001, used to acquire risk data of target personnel;

[0137] The result determination module 1002 is used to input the risk data into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target person; wherein the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target person.

[0138] In one embodiment, the multidimensional analysis model includes multiple risk assessment models, and the risk assessment models correspond to the core indicators one by one; the result determination module is used to: obtain the weight corresponding to each core indicator; input the risk data into the corresponding risk assessment model for risk assessment processing, and determine the indicator value corresponding to each core indicator; determine the risk assessment result of the target person according to the weight and indicator value corresponding to each core indicator.

[0139] In one of the embodiments, the above-mentioned result determination module is specifically used to: add the product of the weight corresponding to each core indicator and the indicator value to obtain a total indicator value; and determine the risk assessment result of the target person based on the total indicator value and a preset indicator threshold.

[0140] In one of the embodiments, the above-mentioned device is also used to: obtain target generalized information data; input the target generalized information data into a clustering model for clustering analysis and processing to obtain core indicators.

[0141] In one embodiment, the target generalized information data includes multiple data points; the device is also used to: input each data point into a clustering model for random selection processing to determine multiple initial cluster centers; calculate the distance between each data point and each initial cluster center to obtain multiple distance results; classify each data point to the corresponding initial cluster center according to the distance result to obtain a classification result; and determine the core indicator according to the classification result.

[0142] In one of the embodiments, the data acquisition module is used to: acquire initial generalized information data; the initial generalized information data includes equipment indicator data, environmental indicator data and personnel status indicator data; and perform data cleaning, data integration and data conversion processing on the equipment indicator data, environmental indicator data and personnel status indicator data in turn to obtain target generalized information data.

[0143] In one of the embodiments, the above-mentioned device is also used to: input the risk assessment result of the target person into the feature extraction model for prediction processing to obtain the prediction result; when the prediction result meets the warning condition, output the warning information.

[0144] In one embodiment, the risk assessment result includes a risk assessment text; the risk assessment result of the target person is input into a feature extraction model for prediction processing, and the prediction result obtained includes:

[0145] Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features;

[0146] Perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text;

[0147] The predicted text corresponding to the maximum probability is determined as the prediction result.

[0148] Each module in the above-mentioned personal risk assessment device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0149] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a personal risk assessment method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0150] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0152] Obtain risk data of target personnel;

[0153] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0154] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0155] Get the weights corresponding to each core indicator;

[0156] Input the risk data into the corresponding risk assessment model for risk assessment processing and determine the indicator values ​​corresponding to each core indicator;

[0157] Determine the risk assessment results of the target personnel based on the weights and indicator values ​​corresponding to each core indicator.

[0158] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0159] Add the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value;

[0160] Determine the risk assessment results of the target personnel based on the total indicator value and the preset indicator threshold.

[0161] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0162] Obtain target generalized information data;

[0163] The target generalized information data is input into the clustering model for clustering analysis to obtain the core indicators.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] Each data point is input into the clustering model for random selection to determine multiple initial cluster centers;

[0166] Calculate the distance between each data point and each initial cluster center to obtain multiple distance results;

[0167] According to the distance results, each data point is classified into the corresponding initial cluster center to obtain the classification result;

[0168] Determine the core indicators based on the classification results.

[0169] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0170] Acquire initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data;

[0171] The equipment index data, environmental index data and personnel status index data are respectively cleaned, integrated and converted to obtain the target generalized information data.

[0172] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0173] The risk assessment results of the target personnel are input into the feature extraction model for prediction processing to obtain the prediction results;

[0174] When the prediction results meet the warning conditions, the warning information is output.

[0175] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0176] Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features;

[0177] Perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text;

[0178] The predicted text corresponding to the maximum probability is determined as the prediction result.

[0179] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0180] Obtain risk data of target personnel;

[0181] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0183] Get the weights corresponding to each core indicator;

[0184] Input the risk data into the corresponding risk assessment model for risk assessment processing and determine the indicator values ​​corresponding to each core indicator;

[0185] Determine the risk assessment results of the target personnel based on the weights and indicator values ​​corresponding to each core indicator.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] Add the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value;

[0188] Determine the risk assessment results of the target personnel based on the total indicator value and the preset indicator threshold.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0190] Obtain target generalized information data;

[0191] The target generalized information data is input into the clustering model for clustering analysis to obtain the core indicators.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] Each data point is input into the clustering model for random selection to determine multiple initial cluster centers;

[0194] Calculate the distance between each data point and each initial cluster center to obtain multiple distance results;

[0195] According to the distance results, each data point is classified into the corresponding initial cluster center to obtain the classification result;

[0196] Determine the core indicators based on the classification results.

[0197] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0198] Acquire initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data;

[0199] The equipment index data, environmental index data and personnel status index data are respectively cleaned, integrated and converted to obtain the target generalized information data.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] The risk assessment results of the target personnel are input into the feature extraction model for prediction processing to obtain the prediction results;

[0202] When the prediction results meet the warning conditions, the warning information is output.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features;

[0205] Perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text;

[0206] The predicted text corresponding to the maximum probability is determined as the prediction result.

[0207] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0208] Obtain risk data of target personnel;

[0209] The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment results of the target personnel; wherein, the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target personnel.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0211] Get the weights corresponding to each core indicator;

[0212] Input the risk data into the corresponding risk assessment model for risk assessment processing and determine the indicator values ​​corresponding to each core indicator;

[0213] Determine the risk assessment results of the target personnel based on the weights and indicator values ​​corresponding to each core indicator.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0215] Add the product of the weight corresponding to each core indicator and the indicator value to obtain the total indicator value;

[0216] Determine the risk assessment results of the target personnel based on the total indicator value and the preset indicator threshold.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] Obtain target generalized information data;

[0219] The target generalized information data is input into the clustering model for clustering analysis to obtain the core indicators.

[0220] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0221] Each data point is input into the clustering model for random selection to determine multiple initial cluster centers;

[0222] Calculate the distance between each data point and each initial cluster center to obtain multiple distance results;

[0223] According to the distance results, each data point is classified into the corresponding initial cluster center to obtain the classification result;

[0224] Determine the core indicators based on the classification results.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] Acquire initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data;

[0227] The equipment index data, environmental index data and personnel status index data are respectively cleaned, integrated and converted to obtain the target generalized information data.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0229] The risk assessment results of the target personnel are input into the feature extraction model for prediction processing to obtain the prediction results;

[0230] When the prediction results meet the warning conditions, the warning information is output.

[0231] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0232] Input the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features;

[0233] Perform prediction processing on each text feature to obtain multiple predicted texts and the probability corresponding to each predicted text;

[0234] The predicted text corresponding to the maximum probability is determined as the prediction result.

[0235] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0236] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0237] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0238] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A personal risk assessment method, characterized in that: The method comprises: Obtain risk data of target personnel; The risk data is input into a pre-established multi-dimensional analysis model for risk assessment processing to obtain a risk assessment result for the target person; wherein the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target person.

2. The method according to claim 1, characterized in that The multidimensional analysis model includes a plurality of risk assessment models, and the risk assessment models correspond to the core indicators one by one; the risk data is input into the pre-established multidimensional analysis model for risk assessment processing to obtain the risk assessment result of the target person, including: Obtaining the weight corresponding to each of the core indicators; Input the risk data into the corresponding risk assessment model to perform risk assessment processing, and determine the indicator value corresponding to each of the core indicators; The risk assessment result of the target person is determined based on the weights and indicator values ​​corresponding to each of the core indicators.

3. The method according to claim 2, characterized in that Determining the risk assessment result of the target person according to the weights and indicator values ​​corresponding to each of the core indicators includes: The product of the weight corresponding to each core indicator and the indicator value is added together to obtain the total indicator value; The risk assessment result of the target person is determined based on the total indicator value and the preset indicator threshold.

4. The method according to any one of claims 1 to 3, characterized in that: The process of determining the core indicators includes: Obtain target generalized information data; The target generalized information data is input into a clustering model for clustering analysis to obtain the core indicators.

5. The method according to claim 4, characterized in that The target generalized information data includes a plurality of data points; the target generalized information data is input into a clustering model for clustering analysis to obtain the core indicators, including: Inputting each of the data points into the clustering model for random selection to determine a plurality of initial clustering centers; Calculating the distance between each of the data points and each of the initial cluster centers to obtain multiple distance results; Classifying each of the data points into a corresponding initial cluster center according to the distance result to obtain a classification result; The core indicator is determined according to the classification result.

6. The method according to claim 4, characterized in that The obtaining of target generalized information data includes: Acquiring initial generalized information data; the initial generalized information data includes equipment index data, environmental index data and personnel status index data; The equipment index data, the environmental index data and the personnel status index data are respectively subjected to data cleaning, data integration and data conversion processing in sequence to obtain the target generalized information data.

7. The method according to claim 1, characterized in that The method comprises: Inputting the risk assessment result of the target person into the feature extraction model for prediction processing to obtain a prediction result; When the prediction result meets the warning condition, the warning information is output.

8. The method according to claim 7, characterized in that The risk assessment result includes a risk assessment text; the risk assessment result of the target person is input into a feature extraction model for prediction processing, and the prediction result obtained includes: Inputting the risk assessment text into the feature extraction model for feature extraction processing to obtain multiple text features; Performing prediction processing on each of the text features to obtain a plurality of predicted texts and probabilities corresponding to each of the predicted texts; The predicted text corresponding to the maximum probability is determined as the prediction result.

9. A personal risk assessment device, characterized in that: The device comprises: A data acquisition module is used to obtain risk data of target personnel; The result determination module is used to input the risk data into a pre-established multi-dimensional analysis model for risk assessment processing to obtain the risk assessment result of the target person; wherein the multi-dimensional analysis model is constructed based on core indicators of multiple assessment dimensions, and the core indicators are used to quantitatively assess the degree of personal risk of the target person.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images