Enterprise environment risk level assessment method and system

Abstract

The invention provides an enterprise environment risk level assessment method and system. The method comprises the steps of obtaining enterprise environment data of an enterprise in a preset operation time period and operation state data of enterprise equipment and / or facilities; performing feature extraction on the operation state data, and inputting a corresponding feature value after extraction into a trained equipment and / or facility operation state evaluation model for prediction processing so as to determine an operation state evaluation value of the enterprise equipment and / or facility in a preset operation time period; determining at least one enterprise operation index evaluation value of the enterprise in the target operation time period based on a correlation coefficient between the environment data of the enterprise environment data under the corresponding evaluation dimension index and the operation state evaluation value; and determining the risk level of the enterprise in the target operation time period according to the at least one enterprise operation index evaluation value. The enterprise operation environment is monitored and evaluated, the accuracy of enterprise environment risk management and control is improved, and the safety of the enterprise operation environment is ensured.

Description

Technical Field

[0001] This invention relates to the field of environmental risk assessment technology for enterprises with pollution sources, and in particular to a method and system for assessing the environmental risk level of an enterprise. Background Technology

[0002] In the process of providing products or services to society during normal production and operation, enterprises continuously face different types and levels of environmental and safety risks and hazards from within the enterprise or from outside the enterprise's location. These risks and hazards constantly threaten the enterprise's production and operation activities, and if they are not identified and controlled, there is always the possibility of losses due to these risks and hazards. For enterprises that are polluting sources, it is necessary to first identify various "hazards" and control them to control the "probability" of these "hazards" occurring, and minimize the loss to the enterprise. Therefore, the goal of "risk" control is to identify various "hazards". Enterprise environmental risks include the risk of illegal and non-compliant emissions of pollutants exceeding the standards at various total discharge outlets after the pollutants are treated during the enterprise's production process, as well as the risk of illegal and non-compliant emissions during the generation, collection, and treatment of various pollutants during the enterprise's production process, and the risk of accidental leakage that pollutes the ecological environment. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for assessing the environmental risk level of enterprises, so as to improve the accuracy and efficiency of enterprise environmental risk management and control.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] A method for assessing corporate environmental risk levels, comprising:

[0006] Acquire enterprise environmental data and operational status data of enterprise equipment and / or facilities within a preset operating period; the operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions and indicators;

[0007] Feature extraction is performed on the operational status data, and the extracted feature values ​​are input into a trained operational status assessment model for equipment and / or facilities for prediction processing to determine the operational status assessment value of the enterprise's equipment and / or facilities within a preset operating period. The operational status assessment model for equipment and / or facilities is obtained by training the historical operational status label values ​​of the equipment and / or facilities and the corresponding historical operational status data based on a preset gradient boosting model.

[0008] Based on the correlation coefficient between the enterprise environmental data and the operational status assessment value under the corresponding assessment dimension indicators, the assessment value of at least one enterprise operational indicator is determined for the enterprise during the target operational period.

[0009] The risk level of the enterprise during the target operating period is determined based on the assessment value of at least one of the enterprise operation indicators.

[0010] Embodiments of the present invention also provide a risk level assessment system for an enterprise operating environment, comprising:

[0011] The acquisition module is used to acquire enterprise environmental data and operational status data of enterprise equipment and / or facilities within a preset operating period; the operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions and indicators;

[0012] The processing module is used to extract features from the operational status data and input the extracted feature values ​​into a trained operational status assessment model for predictive processing, so as to determine the operational status assessment value of the enterprise's equipment and / or facilities within a preset operating period. The operational status assessment model is obtained by training the historical operational status label values ​​and corresponding historical operational status data of the equipment and / or facilities based on a preset gradient boosting model. Based on the correlation coefficient between the enterprise's environmental data and the operational status assessment value under the corresponding assessment dimension indicator, at least one enterprise operational indicator assessment value is determined for the enterprise within the target operating period. Based on at least one enterprise operational indicator assessment value, the risk assessment value of the enterprise during operation within the target operating period and the risk level corresponding to the risk assessment value are determined.

[0013] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above.

[0014] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0015] The above-described solution of the present invention has at least the following beneficial effects:

[0016] The above-described solution of the present invention acquires enterprise environmental data and enterprise operational status data within a preset operating period. The operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions. Features are extracted from the operational status data, and the extracted feature values ​​are input into a trained equipment and / or facility operational status evaluation model for prediction processing to determine the operational status evaluation value of the enterprise's equipment and / or facilities within the preset operating period. The equipment and / or facility operational status evaluation model is trained based on a preset gradient boosting model using historical operational status tag values ​​and corresponding historical operational status data of the equipment and / or facilities. Based on the correlation coefficient between the enterprise environmental data under the corresponding evaluation dimensions and the operational status evaluation value, at least one enterprise operational indicator evaluation value is determined for the enterprise within the target operating period. Based on at least one of the enterprise operational indicator evaluation values, the risk level of the enterprise within the target operating period is determined. By analyzing and processing large-scale and complex data on enterprise equipment and / or facilities using machine learning, it is possible to obtain the indicator evaluation values ​​of each piece of equipment and / or facility. Then, according to the evaluation rules and the indicator values ​​of the equipment and / or facilities, the enterprise's environmental risk level can be obtained. Through the risk level, the monitoring and evaluation of the enterprise's operating environment can be realized, which improves the accuracy of enterprise environmental risk management and ensures the safety of the enterprise's operating environment. Attached Figure Description

[0017] Figure 1 This is a flowchart of the enterprise environmental risk level assessment method provided in the embodiments of the present invention;

[0018] Figure 2 This is a schematic diagram of the module block of the risk level assessment system for the enterprise operating environment provided in an embodiment of the present invention;

[0019] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of the present invention;

[0020] Figure 4 This is a schematic block diagram of a computing device provided in an embodiment of the present invention. Detailed Implementation

[0021] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0022] like Figure 1As shown, an embodiment of the present invention proposes a method for assessing the environmental risk level of an enterprise, including:

[0023] Step 11: Obtain enterprise environmental data and operational status data of enterprise equipment and / or facilities within a preset operating period; the operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions.

[0024] Step 12: Extract features from the operational status data and input the extracted feature values ​​into the trained equipment and / or facility operational status assessment model for prediction processing to determine the operational status assessment value of the enterprise's equipment and / or facilities within a preset operating period; the equipment and / or facility operational status assessment model is obtained by training the historical operational status label values ​​of the equipment and / or facilities and the corresponding historical operational status data based on a preset gradient boosting model.

[0025] Step 13: Based on the correlation coefficient between the enterprise environmental data and the operational status assessment value under the corresponding assessment dimension indicators, determine the assessment value of at least one enterprise operation indicator for the target operating period.

[0026] Step 14: Determine the risk level of the enterprise during the target operating period based on the assessment value of at least one of the enterprise operation indicators.

[0027] In this embodiment, enterprise environmental data refers to the external natural ecological environment and the internal production environment of the enterprise during the production and operation activities. Since the enterprise generates and emits ecological and environmental pollutants at various stages during the production and operation activities, the internal production environment is the main management target to avoid the pollutants generated in the internal production environment from having an adverse impact on the external natural ecological environment.

[0028] Risk refers to uncertain events that may occur in the future, including the probability of an accident occurring and the severity of its consequences. Risk is objective, uncertain, and universal; it is a combination of the likelihood of a specific hazardous event occurring and the severity of its consequences.

[0029] The assessment dimensions and indicators include air pollution (exhaust gas), water pollution (wastewater), soil pollution (waste chemicals, etc.), and solid waste pollution (waste residue). These indicators are used to assess the impact of a company's internal production environment on the natural ecological environment during its production and operation activities.

[0030] The equipment of an enterprise mainly refers to industrial production equipment such as production equipment, fire-fighting equipment, and emission equipment. Facilities mainly include industrial infrastructure such as sewage pipelines and sewage treatment ponds. The operational status data of the enterprise's equipment and / or facilities mainly refers to the operating time, equipment temperature, the total number of equipment and / or facilities operating within the same time period, and the operating parameters of key components within the equipment and / or facilities. This operational status data can be obtained by installing multiple sensors within the enterprise.

[0031] This embodiment combines enterprise environmental data with operational status data of equipment and / or facilities. Based on the correlation between these two data, an enterprise operational indicator assessment value is obtained. This assessment value is then used to determine the enterprise's current risk level. By understanding the enterprise's risk level, the operating environment can be monitored and assessed in real time, and corresponding management systems and work guidelines can be developed to facilitate full lifecycle management.

[0032] This embodiment uses machine learning to analyze and process large-scale and complex data on enterprise equipment and / or facilities, enabling the monitoring and evaluation of the enterprise's operating environment, improving the accuracy of enterprise environmental risk management, and ensuring the security of the enterprise's operating environment.

[0033] In an optional embodiment of the present invention, step 12 above may include:

[0034] Step 121: Based on the operating status data, determine at least one target operating condition corresponding to the enterprise's equipment and / or facilities;

[0035] Step 122: Perform clustering processing on the operating status data corresponding to at least one of the target operating conditions to obtain at least one cluster of operating status data corresponding to the target operating conditions; determine the feature value of the operating status data corresponding to the target operating conditions based on the operating status data corresponding to the target operating conditions in the cluster.

[0036] In this embodiment, the target operating condition refers to one or more of the following operating status data: the running time of the equipment and / or facility, the speed of the motor in the equipment and / or facility, and the operating temperature of the equipment and / or facility. For example, the operating conditions (motor speed, temperature, etc.) of the motor in the "start" state, "idle" state, and "full load" state. By dividing the data into cluster centers, the clustering results are used as the target operating conditions, and a sequence of operating condition labels (such as the operating condition category corresponding to the timestamp) is generated to label the input operating status data segment (which may be data of a time window) with the corresponding target operating condition label.

[0037] Considering that even under the same target operating condition, equipment and / or facilities may be in different actual states, further clustering is performed on the actual operating status data (mainly sensor readings) of equipment and / or facilities under the same target operating condition based on operating condition labels to discover different state patterns or clusters within the data. Specifically, the original data is divided into multiple subsets according to operating condition type, the data in the subsets are normalized, and then the K-Means algorithm is used to cluster the subsets of each operating condition again to obtain at least one cluster of operating status data corresponding to the target operating condition. Each operating status data belonging to the same target operating condition is assigned a cluster label to discover different operating modes under the same operating condition, such as operating condition A operating normally, or operating condition A operating abnormally.

[0038] Furthermore, according to the time series, for each operating status data, multiple features are calculated and combined into a single feature value based on its target operating condition and cluster. This feature value integrates operating condition information (through step 121) and information on the specific operating status pattern under that operating condition (through clustering and cluster-based feature calculation in step 122).

[0039] In an optional embodiment of the present invention, step 121 above may include:

[0040] Step 1211: Preprocess the running status data to obtain preprocessed running status data;

[0041] Step 1212: Based on the preset fitting model and the preprocessed running state data, obtain the predicted value corresponding to each preprocessed running state data.

[0042] Step 1213: Based on the correlation coefficient between the preprocessed operating status data and the corresponding predicted value, determine at least one target operating condition corresponding to the enterprise equipment and / or facilities within the preset operating period.

[0043] In this embodiment, in the process of determining at least one target operating condition corresponding to the enterprise's equipment and / or facilities based on the operating status data, the original equipment and / or facility operating data is first converted into a standardized format suitable for subsequent analysis to eliminate noise and invalid information interference. Missing points in the detected equipment and / or facility operating status data are filled in, which can be done using interpolation (calculating reasonable values ​​from preceding and following data) or deletion (removing invalid segments). Then, outliers in the filled data are removed. Finally, the data is reduced to a standard normal distribution (mean 0, standard deviation 1) to avoid analytical bias caused by differences in magnitude, resulting in preprocessed data.

[0044] Furthermore, predicted values ​​are generated based on a pre-defined fitting model and preprocessed data. This fitting model is obtained by fitting historical operating data and operating time, representing the relationship between historical operating data and operating time. The preprocessed data is input into the model, with the input variables being the current operating data of the equipment and / or facilities, and the output variable being the predicted operating data of the equipment and / or facilities at a future time or time period, which can be represented in the form of a working condition reference curve.

[0045] Next, based on the correlation coefficient between the preprocessed operating status data and the corresponding predicted value, at least one target operating condition corresponding to the enterprise equipment and / or facilities within the preset operating period is determined, that is, the operating state of the target equipment and / or facilities.

[0046] Within a preset time window (e.g., 30 minutes), calculate the actual operating status value y during that period. i Compared with the predicted operating status Correlation coefficient R:

[0047] Results range: [-1, 1], the closer to 1, the higher the linear correlation between actual and predicted behavior.

[0048] The fundamental relevance is determined by the target operating condition, and the determination logic is as follows:

[0049] A high correlation (r≥0.8) indicates a healthy operating condition;

[0050] A correlation coefficient of 0.5 ≤ r < 0.8 indicates a declining operating condition.

[0051] Low correlation (r<0.5) indicates a fault condition.

[0052] In an optional embodiment of the present invention, step 12 may further include:

[0053] Step 123: Input the feature value corresponding to the target working condition into at least one weak learner of the equipment and / or facility operation status evaluation model for processing to obtain at least one residual;

[0054] Step 124: The sum of the residuals of the at least one weak learner is iteratively input into the strong learner of the equipment and / or facility operation status assessment model for processing to obtain the output result of the strong learner;

[0055] Step 125: The output of the strong learner is evaluated and predicted to determine the operational status evaluation value of the enterprise equipment and / or facilities during a preset operating period.

[0056] In this embodiment, the characteristic values ​​corresponding to the target operating conditions are analyzed and processed by the trained equipment and / or facility operation status assessment model to determine the target operating conditions corresponding to the current operating status of the equipment and / or facilities, so as to ensure the accuracy of subsequent determination of operation status assessment values ​​based on different target operating conditions.

[0057] The equipment and / or facility operation status assessment model is trained on a pre-defined gradient boosting model using historical operation status label values ​​and corresponding historical operation status data of the equipment and / or facilities. Different operation states of the equipment and / or facilities correspond to different target operating conditions, including healthy operating conditions (healthy operation status), deteriorating operating conditions (deteriorating operation status), and fault operating conditions (fault operating status). The operation status data and label values ​​for each target operating condition are different. For example, the label value for the first operating condition (healthy operation status) is 80-100, the label value for the second operating condition (deteriorating operation status) is 60-70, and the label value for the third operating condition (fault operating status) is 0-40. The model is trained using historical time-series data. The training process of this model is the same as the actual operation process, and the specific training process is as follows:

[0058] Step 21: Obtain training set data, which includes: historical running state data corresponding to the first historical running state label value, historical running state data corresponding to the second historical running state label value, and historical running state data corresponding to the third historical running state label value.

[0059] Step 22: Perform feature transformation on the training set data to obtain training feature data;

[0060] Step 23: Input the training feature data into at least one weak learner of the preset network model for processing to obtain at least one residual;

[0061] Step 24: The sum of the residuals output by each weak learner is iteratively input into the strong learner of the preset network model for processing to obtain the output result of the strong learner.

[0062] Step 25: Perform prediction processing on the output of the strong learner to obtain the trained equipment and / or facility operation status assessment model and training prediction results.

[0063] Here, the transformed and processed data is used as training feature data and input into a preset network model for simulation training in order to obtain the minimization objective function and the optimal parameters of the objective function;

[0064] Feature transformation is performed on the historical running state data corresponding to the first, second, and third historical running state label values. The transformed feature data is then divided into training feature data (training data sample set) and validation feature data (validation data sample set). The training sample dataset is input into at least one weak learner of a pre-defined network model to train the first CART tree. This tree is then used to predict the training set, obtaining the predicted value for each training sample. Since there is a deviation between the predicted value and the true value of the validation sample, the two are subtracted to obtain the residual. Next, the second CART tree is trained, but the initial historical data is no longer used for feature transformation. Instead of using the true value of the validation sample obtained from the training of the first CART tree, the residual of the first CART tree is used as the true value of the validation sample at this time. After the training of the two trees is completed, the residual of each sample can be obtained again, and then the third tree is trained, and so on. The sum of the residuals of all weak learners in the preset network model is input into the strong learner of the preset network model for training simulation processing to obtain the output result of the strong learner. The output result is then input into the output layer of the preset network model for processing. The model parameters are determined by methods such as parameter tuning, and thus a trained equipment and / or facility operation status evaluation model is obtained. The output result of the strong learner is weighted and summed to obtain the weighted sum result, which can be used as the training prediction result of the model.

[0065] Here, the preset network model can be an XGBoost model. The specific training process for training a CART tree by inputting the training sample dataset into at least one weak learner of the preset network model is as follows:

[0066] Step 31: Input the training feature data into at least one weak learner of the XGBoost model and adjust the parameters of the XGBoost model, which may include tree depth, learning rate and number of iterations.

[0067] Step 32: Iteratively process the data in the training feature dataset, generating a new decision tree in each iteration. The specific steps of each iteration include:

[0068] Step 321: Before each iteration, calculate the first and second derivatives of the loss function (objective function) at each training sample point;

[0069] Step 322: Generate a new decision tree using a greedy strategy, and calculate the predicted value for each leaf node by taking the parameter values ​​corresponding to the leaf nodes.

[0070] Step 323: Add the newly generated decision tree to the trained preset network model.

[0071] Step 33: Determine if the loss function has reached its minimum. If yes, proceed to step 34; otherwise, proceed to step 32.

[0072] Step 34: Input the data from the validation dataset into the preset network model for training, calculate the evaluation index, and determine whether the evaluation index meets the required value. If yes, save the model; otherwise, proceed to step 31.

[0073] During the iterative computation of the training feature dataset in the preset network model, the network calculates the gradient of the batch loss with respect to the weights and updates the weights accordingly. After multiple rounds of computation, the network loss value becomes sufficiently small. The weights are trained using the gradient backpropagation algorithm to enhance the model's self-learning performance. Ten-fold cross-validation is used to adjust the parameters of the preset network model, further improving the accuracy of classification processing. The loss function can be expressed by the following formula:

[0074]

[0075] Where S is the loss value, K represents the total number of weak learners (decision trees), f k (x i ) indicates that the strong learner is effective for sample x. i The predicted value, This represents the training error term, used to measure the model's predicted values. Compared with the true value y i The difference between them, ω(f) k ) represents the regularization term of the k-th weak learner (by adding a regularization term, the complexity of the model is controlled, and overfitting is prevented). Specifically, it can be represented as: Where γ represents the first regularization parameter, which controls the influence of the number of leaf nodes in the decision tree on the loss function; τ represents the number of leaf nodes in the decision tree; λ represents the second regularization parameter, which controls the L2 penalty of the regularization term for the weights of the leaf nodes; and ω represents the weight vector on the leaf node.

[0076] During training, the loss function is optimized, and the optimized loss function S′ can be expressed as:

[0077]

[0078] in, h represents the first derivative of the loss function at the current predicted value. i = This represents the second derivative of the loss function at the current predicted value; iterative training of the weak learner: at the t-th iteration, t-1 decision trees have been built, and the model's predicted value is... At this point, it is necessary to train the t-th decision tree f.t To make the new model predictions To better fit the data, f is determined by minimizing the loss function. t .

[0079] In an optional embodiment of the present invention, step 13 above may include:

[0080] Step 131: Based on the enterprise environment data and the operation status evaluation value, construct a grey relational system of the enterprise operation environment, and determine the grey relational coefficient of the grey relational system under the corresponding evaluation dimension index.

[0081] Step 132: Based on the grey relational coefficient of the grey relational system under the corresponding evaluation dimension index and the target operating status data within the target operating period, determine the evaluation value of at least one enterprise operating indicator for the enterprise within the target operating period.

[0082] In this embodiment, based on the environmental data of the enterprise environment under the corresponding evaluation dimension indicators, the reference sequence of the gray relational system of the enterprise operating environment under the corresponding evaluation dimension indicators is determined.

[0083] The reference sequence (X0) represents the enterprise's operational status assessment value. This is a time series data set, with a value for each point in time (e.g., daily, weekly, monthly, hourly), reflecting the enterprise's operational status at that moment.

[0084] Compare sequences (X1, X2, X3, ..., X m These represent enterprise environmental data under various assessment dimensions. Each series corresponds to a specific environmental indicator, such as air quality indicators, water pollution indicators, soil indicators, and solid waste indicators. Similarly, each series is also time series data, corresponding one-to-one with the time points of the reference series.

[0085] The grey relational coefficient is for each specific time point k and each comparison sequence X. i The degree of correlation with the reference sequence X0 at this point:

[0086]

[0087] Δ i (k)=|X′0(k)-X′ i (k)|;

[0088] Δ min =min i mink|X′0(k)-X′ i (k)|;

[0089] Δ max =maxi maxk|X′0(k)-X′ i (k)|;

[0090] Next, for a certain environmental indicator i, its correlation coefficient δ at all n time points is calculated. i (1),δ i 2,...,δ i (n) Calculate the arithmetic mean. This mean r i It is the grey relational coefficient between the environmental indicator i and the enterprise's operating status throughout the entire historical analysis period.

[0091]

[0092] Finally, the grey relational coefficient vector [r1, r2, ..., r] is obtained. m ], r i ∈[0,1]. r i The larger the value, the more similar and closely related the changing trend of environmental indicator i is to the changing trend of the enterprise's operating status X0 throughout the entire historical analysis period. The more significant the impact of this indicator on the operating status is considered.

[0093] Where, Δ i (k) represents the value of the reference sequence X′0 and the comparison sequence X′ at time point k. i The absolute difference between the values. This measures how close the two sequences of data are at that moment.

[0094] Δ min Let i be the minimum absolute difference between all comparison sequences i and the reference sequence at all time points k.

[0095] Δ max Let i be the maximum absolute difference between all comparison sequences i and the reference sequence at all time points k.

[0096] ρ is the discrimination coefficient, a constant between 0 and 1 (usually taken as 0.5). It is used to adjust the significance of differences in correlation coefficients. The smaller ρ is, the greater the difference in correlation coefficients and the stronger the discrimination ability; the larger ρ is, the smaller the difference in correlation coefficients and the stronger the resistance to interference.

[0097] Furthermore, based on the grey relational coefficient and the environmental data actually monitored during the target operating period, the overall impact or status of various environmental indicators on the enterprise's operating status during the target period is assessed.

[0098] Obtain target operating status data Y within the target operating period. i = [Y1, Y2, ..., Y] m Using the grey relational coefficient r i For Y iPerform weighted synthesis to obtain the evaluation value q of the enterprise operation indicators i :

[0099]

[0100] In an optional embodiment of the present invention, the above step 14 may include:

[0101] Step 141, determine the risk evaluation value of the enterprise during the target operation period:

[0102] Step 142, obtain the risk level during the target operation period according to the risk evaluation value;

[0103] In this embodiment, after the scoring of each sub-item and the weight configuration are completed, calculate the comprehensive score to obtain the risk evaluation value:

[0104]

[0105] Where Q represents the risk evaluation value; q i represents the evaluation value of the i-th type of enterprise operation indicator; m i represents the weight corresponding to the evaluation value of the i-th type of enterprise operation indicator; j represents the total number of types of evaluation dimension indicators in the enterprise environmental data; i = 1, 2, 3,..., j is a positive integer.

[0106] Finally, according to the corresponding relationship between the risk evaluation value and the preset risk level table, obtain the risk level during the target operation period. Monitor and evaluate the enterprise operation environment according to the risk level.

[0107] A specific example:

[0108] 0 < Q ≤ 3, no risk;

[0109] 3 < Q ≤ 6, general risk;

[0110] 6 < Q ≤ 9, relatively large risk;

[0111] 9 < Q ≤ 12, major risk.

[0112] The method of the above embodiment of the present invention analyzes and processes the large-scale and complex data of enterprise equipment and / or facilities based on machine learning, can realize the monitoring and evaluation of the enterprise operation environment, improves the accuracy of enterprise environmental risk control, and ensures the safety of the enterprise operation environment.

[0113] As Figure 2 shown, the embodiment of the present invention also provides a risk level evaluation system 20 for the enterprise operation environment, including:

[0114] The acquisition module 21 is used to acquire enterprise environmental data and enterprise equipment and / or facility operation status data within a preset operating period; the operation status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimension indicators;

[0115] Processing module 22 is used to extract features from the operational status data and input the extracted feature values ​​into a trained equipment and / or facility operational status assessment model for prediction processing, so as to determine the operational status assessment value of the enterprise's equipment and / or facilities within a preset operational period. The equipment and / or facility operational status assessment model is trained on the historical operational status label values ​​of the equipment and the corresponding historical operational status data based on a preset gradient boosting model. Based on the correlation coefficient between the enterprise's environmental data and the operational status assessment value under the corresponding assessment dimension indicator, at least one enterprise operational indicator assessment value is determined for the enterprise within the target operational period. Based on at least one of the enterprise operational indicator assessment values, the risk assessment value of the enterprise during operation within the target operational period and the risk level corresponding to the risk assessment value are determined.

[0116] It should be noted that this device is a device corresponding to the above-mentioned enterprise environmental risk level assessment method. All implementation methods in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0117] like Figure 3 As shown, embodiments of the present invention also provide an electronic device 30, comprising: a memory 31 for storing one or more computer programs; and one or more processors 32 for executing the one or more computer programs. When the computer programs are run by the processors, they execute the method for determining village and town development patterns based on POI data as described in the above method embodiments. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects. The electronic device 30 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown in this invention, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0118] like Figure 4As shown, electronic device 30 is a computing device or computer system, which may include CPU 301 (computing unit), which can perform various appropriate actions and processes according to a computer program stored in ROM 302 (read-only memory) or a computer program loaded from storage unit 308 into random access RAM 303 (memory). RAM 303 may also store various programs and data required for device operation. CPU 301, ROM 302, and RAM 303 are interconnected via bus 304. I / O interface 305 (input / output interface) is also connected to bus 304.

[0119] Multiple components in electronic device 30 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0120] CPU 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of CPU 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. CPU 301 performs the various methods and processes described above. For example, in some embodiments, the method for determining village and town development patterns based on POI data can be implemented as a computer software program tangibly contained in a computer-readable storage medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the device via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by CPU 301, one or more steps of the method for determining village and town development patterns based on POI data described in the above method embodiments can be performed. Alternatively, in other embodiments, CPU 301 can be configured to perform the method for determining village and town development patterns based on POI data by any other suitable means (e.g., by means of firmware).

[0121] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method for determining village and town development patterns based on POI data as described in the above method embodiments. All implementations of the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0122] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0123] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0124] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0126] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0127] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0128] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0129] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps for performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0130] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for assessing the environmental risk level of an enterprise, characterized in that, include: Acquire enterprise environmental data and operational status data of enterprise equipment and / or facilities during preset operating periods; The operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions and indicators; Feature extraction is performed on the operational status data, and the extracted feature values ​​are input into a trained operational status assessment model for equipment and / or facilities for prediction processing to determine the operational status assessment value of the enterprise's equipment and / or facilities within a preset operating period. The operational status assessment model for equipment and / or facilities is obtained by training the historical operational status label values ​​of the equipment and / or facilities and the corresponding historical operational status data based on a preset gradient boosting model. Based on the correlation coefficient between the enterprise environmental data and the operational status assessment value under the corresponding assessment dimension indicators, the assessment value of at least one enterprise operational indicator is determined for the enterprise during the target operational period. The risk level of the enterprise during the target operating period is determined based on the assessment value of at least one of the enterprise operation indicators.

2. The enterprise environmental risk level assessment method according to claim 1, characterized in that, Feature extraction of the operational status data includes: Based on the operational status data, at least one target operating condition corresponding to the enterprise's equipment and / or facilities is determined; Clustering processing is performed on the operating status data corresponding to at least one of the target operating conditions to obtain at least one cluster of operating status data corresponding to the target operating conditions; Based on the operating status data corresponding to the target operating condition in the cluster, the feature values ​​of the operating status data corresponding to the target operating condition are determined.

3. The enterprise environmental risk level assessment method according to claim 2, characterized in that, Based on the operational status data, at least one target operating condition corresponding to the enterprise's equipment and / or facilities is determined, including: The operation status data is preprocessed to obtain preprocessed operation status data; Based on the preset fitting model and the preprocessed running status data, the predicted value corresponding to each preprocessed running status data is obtained; Based on the correlation coefficient between the preprocessed operating status data and the corresponding predicted values, at least one target operating condition corresponding to the enterprise equipment and / or facilities within a preset operating period is determined.

4. The enterprise environmental risk level assessment method according to claim 3, characterized in that, The extracted feature values ​​are input into a trained equipment and / or facility operation status assessment model for prediction processing to determine the operation status assessment values ​​of the enterprise's equipment and / or facilities within a preset operating period, including: The feature value corresponding to the target operating condition is input into at least one weak learner of the operating status evaluation model of the equipment and / or facility for processing to obtain at least one residual. The sum of the residuals of the at least one weak learner is iteratively input into the strong learner of the equipment and / or facility operation status assessment model for processing to obtain the output result of the strong learner. The output of the strong learner is evaluated and predicted to determine the operational status assessment value of the enterprise equipment and / or facilities during a preset operating period.

5. The enterprise environmental risk level assessment method according to claim 1, characterized in that, Based on the correlation coefficient between the enterprise's environmental data and the operational status assessment value under the corresponding assessment dimension indicators, at least one enterprise operational indicator assessment value is determined for the enterprise during the target operational period, including: Based on the enterprise environment data and the operational status assessment value, a grey relational system of the enterprise operating environment is constructed, and the grey relational coefficient of the grey relational system under the corresponding assessment dimension index is determined. Based on the grey relational coefficients of the grey relational system under the corresponding evaluation dimension indicators and the target operating status data within the target operating period, the evaluation value of at least one enterprise operating indicator of the enterprise within the target operating period is determined.

6. The enterprise environmental risk level assessment method according to claim 5, characterized in that, Based on the enterprise environment data and the operational status assessment values, a grey relational analysis system for the enterprise's operational environment is constructed, and the grey relational coefficients of the grey relational analysis system under the corresponding assessment dimension indicators are determined, including: Based on the environmental data of the enterprise environment under the corresponding evaluation dimension indicators, determine the reference sequence of the grey relational system of the enterprise operating environment under the corresponding evaluation dimension indicators; Based on the operational status evaluation value, a comparison sequence of the grey relational system of the enterprise's operating environment is determined; Based on the reference sequence and the comparison sequence, determine the grey relational coefficient of the grey relational system of the enterprise operating environment under the corresponding evaluation dimension indicators.

7. The enterprise environmental risk level assessment method according to claim 1, characterized in that, Based on at least one of the aforementioned business operation indicators, determine the enterprise's risk level during the target operating period, including: The risk assessment value for the enterprise during the target operating period is determined using the following formula: Based on the risk assessment values, the risk level for the target operating period is obtained; Where Q represents the risk assessment value; q i m represents the evaluation value of the i-th type of enterprise operation indicator; i represents the weight corresponding to the evaluation value of the i-th type of enterprise operation indicator; j represents the total number of evaluation dimension indicators in the enterprise environmental data; i = 1, 2, 3, ..., j are positive integers.

8. A corporate environmental risk level assessment system, characterized in that, include: The acquisition module is used to acquire enterprise environmental data and operational status data of enterprise equipment and / or facilities during a preset operating period. The operational status data is time-series data containing equipment and / or facility tags, and the enterprise environmental data includes environmental data under multiple evaluation dimensions and indicators; The processing module is used to extract features from the operating status data and input the extracted feature values ​​into a trained equipment and / or facility operating status assessment model for prediction processing, so as to determine the operating status assessment value of the enterprise's equipment and / or facilities within a preset operating period; the equipment and / or facility operating status assessment model is obtained by training the historical operating status label values ​​of the equipment and / or facilities and the corresponding historical operating status data based on a preset gradient boosting model. Based on the correlation coefficient between the enterprise's environmental data and the operational status assessment value under the corresponding assessment dimension indicators, at least one enterprise operational indicator assessment value is determined for the enterprise during the target operational period; based on at least one of the enterprise operational indicator assessment values, the risk assessment value of the enterprise during the target operational period and the risk level corresponding to the risk assessment value are determined.

9. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A storage instruction that, when executed on a computer, causes the computer to perform the method as described in any one of claims 1 to 7.

Images