Big data-based multi-dimensional operation risk assessment method and system

Abstract

The embodiment of the invention provides a multi-dimensional operation risk assessment method and system based on big data, and belongs to the technical field of operation risk assessment of production projects. The evaluation method comprises the following steps: acquiring personnel composition data, equipment composition data, time data and project content data of a current project; generating a first feature map according to the personnel composition data; generating a second feature map according to the equipment composition data; generating a third feature map according to the time data; generating a fourth feature map according to the project content data; combining the first feature map, the second feature map, the third feature map and the fourth feature map to obtain a project attribute feature map; and inputting the project attribute feature map into a preset GCN model to obtain the risk level of the current project. According to the evaluation method and system, the risk level of the production project can be accurately predicted according to various factors of the production project.

Description

Technical Field

[0001] The present invention relates to the technical field of operational risk assessment for production projects, and in particular to a multi-dimensional operational risk assessment method and system based on big data. Background Art

[0002] In the risk assessment of power grid production projects, there are many variables and factors involved, including personnel quality and behavior, equipment operation status, project time nodes, and the impact of the natural environment. There are intricate relationships between these factors, making the entire risk assessment process extremely complex.

[0003] The skill level, work experience and psychological state of production personnel will directly affect the accuracy of operations and the quality of decision-making, thus having a significant impact on production safety. The performance stability, maintenance status and coordination degree of production equipment with other equipment are also factors that must be considered in risk assessment. At the same time, whether the project schedule is reasonable and whether there is sufficient buffer time during the construction process to deal with emergencies are also key factors affecting the smooth progress of the project.

[0004] Weather conditions also have an impact on power grid production projects that cannot be ignored. For example, extreme weather may cause construction delays or equipment failures, increasing project uncertainty. All these factors are intertwined to form a highly complex system, and the identification and assessment of its risk points requires knowledge and technology across different fields.

[0005] Due to the large number of variables involved and the complex interactions between them, the risk assessment of power grid production projects often relies on the subjective judgment of experts, which limits the objectivity and accuracy of the assessment to a certain extent. In addition, traditional risk assessment methods often lack flexibility and are difficult to adapt to the rapidly changing project environment and emerging risk factors, which may cause the assessment results to deviate from the actual situation. Summary of the invention

[0006] The purpose of the embodiments of the present invention is to provide a multi-dimensional operation risk assessment method and system based on big data, which can accurately predict the risk level of a production project based on multiple factors of the production project.

[0007] In order to achieve the above objectives, an embodiment of the present invention provides a multi-dimensional operation risk assessment method based on big data, comprising:

[0008] Obtain personnel composition data, equipment composition data, time data, and project content data of the current project;

[0009] Generate a first feature graph according to the personnel composition data;

[0010] generating a second feature map according to the device configuration data;

[0011] generating a third feature map according to the time data;

[0012] generating a fourth feature map according to the project content data;

[0013] Combining the first feature map, the second feature map, the third feature map and the fourth feature map to obtain an item attribute feature map;

[0014] The project attribute feature map is input into a preset GCN model to obtain the risk level of the current project.

[0015] Optionally, the personnel composition data includes at least one of the age distribution of the personnel, whether they are temporary workers, personnel stability assessment indicators, technical levels, training duration, and personnel historical violation rates.

[0016] Optionally, the equipment composition data includes at least one of equipment service life, equipment service time, maintenance rate of similar equipment, equipment type, equipment hazard level, and historical maintenance times of equipment.

[0017] Optionally, the time data includes at least one of project duration, project start time, and project end time.

[0018] Optionally, the project content data includes at least one of the type of project, the time span of the project, and the scale level of the project.

[0019] Optionally, combining the first feature map, the second feature map, the third feature map and the fourth feature map to obtain an item attribute feature map includes:

[0020] Using the first feature map as the upper left corner of the project attribute feature map;

[0021] Using the second feature map as the lower left corner of the item attribute feature map;

[0022] Using the third feature map as the upper right corner of the project attribute feature map;

[0023] The fourth feature map is used as the lower right corner of the item attribute feature map to form the item attribute feature map.

[0024] Optionally, the evaluation method comprises:

[0025] Constructing a dataset for training the GCN model;

[0026] Divide the data set into a training set, a test set, and a validation set in a ratio of 6:2:2;

[0027] Using the training set to train the GCN model;

[0028] The performance of the GCN model is tested using a test set;

[0029] The validation set is used to verify whether the GCN model meets the accuracy requirements.

[0030] Optionally, using the training set to train the GCN model includes:

[0031] Formula (1) is used as the multi-classification loss function of the GCN model.

[0032]

[0033] Wherein, L is the multi-classification loss function, n is the dimension of the item attribute feature map, y is the output of the GCN model, is the standardized output of the GCN model, and σ is the sigmoid function.

[0034] On the other hand, the present invention also provides a multi-dimensional operational risk assessment system based on big data, wherein the assessment system comprises a processor configured to execute any of the assessment methods described above.

[0035] In yet another aspect, the present invention further provides a computer-readable storage medium storing instructions, wherein the instructions are used to be read by a machine so as to enable the machine to execute any of the above-mentioned evaluation methods.

[0036] Through the above technical solution, the embodiment of the present invention provides a multi-dimensional operation risk assessment method and system based on big data, which constructs a project attribute feature map by acquiring personnel composition data, equipment composition data, time data, and project content data, and predicts the risk level according to the project attribute feature map through the GCN model. Compared with the prior art, the assessment method and system provided by the embodiment of the present invention achieves the accuracy of the risk level of the production project.

[0037] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0039] Figure 1 is a flowchart of a multi-dimensional risk assessment method based on big data according to an embodiment of the present invention;

[0040] Figure 2 is a screenshot of an interface for generating risk levels according to an embodiment of the present invention;

[0041] Figure 3 is a flowchart of a method for obtaining a GCN model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0043] like Figure 1 The figure is a flowchart of a multi-dimensional risk assessment method based on big data according to one embodiment of the present invention. Figure 1 The evaluation method may include the following steps:

[0044] In step S10, the personnel composition data, equipment composition data, time data, and project content data of the current project are obtained;

[0045] In step S11, a first feature graph is generated according to the personnel composition data;

[0046] In step S12, a second feature map is generated according to the device configuration data;

[0047] In step S13, a third feature map is generated according to the time data;

[0048] In step S14, a fourth feature map is generated according to the project content data;

[0049] In step S15, the first feature map, the second feature map, the third feature map and the fourth feature map are combined to obtain an item attribute feature map;

[0050] In step S16, the project attribute feature graph is input into a preset GCN (Graph Convolutional Network) model to obtain the risk level of the current project.

[0051] In this Figure 1In the evaluation method shown, step S10 is used to obtain the personnel composition data, equipment composition data, time data, and project content data of the current project. Among them, the different data characteristics of the personnel composition data, equipment composition data, time data, and project content data are taken into account. In this embodiment, the personnel composition data includes at least one of the age distribution of the personnel, whether they are temporary workers, the stability evaluation index of the personnel, the technical level, the training time, and the historical violation rate of the personnel. The equipment composition data includes at least one of the service life of the equipment, the service time of the equipment, the maintenance rate of similar equipment, the type of equipment, the danger level of the equipment, and the number of historical maintenance times of the equipment. The time data includes at least one of the project duration, the project start time, and the project end time. In addition, due to the seasonal climate distribution of the construction area, the time data can also include meteorological data. The project content data includes at least one of the type of project, the time span of the project, and the scale level of the project.

[0052] Steps S11 to S14 are used to generate the first to fourth feature graphs according to the personnel composition data, the equipment composition data, the time data, and the project content data, respectively. Considering the dimensional characteristics of the first to fourth feature graphs, in this embodiment, the process of generating the project attribute feature graph in step S15 can be to use the first feature graph as the upper left corner of the project attribute feature graph, the second feature graph as the lower left corner of the project attribute feature graph, the third feature graph as the upper right corner of the project attribute feature graph, and the fourth feature graph as the lower right corner of the project attribute feature graph to form the project attribute feature graph.

[0053] Step S16 can be used to input the project attribute feature map into a preset GCN model to obtain the risk level of the current project. The schematic diagram of the interface for generating the risk level can be as follows: Figure 2 As shown. Among them, the specific method for obtaining the GCN model can be various forms known to those skilled in the art. In one example of the present invention, the method for obtaining the GCN model can include: Figure 2 The steps shown. Figure 2 In the method for obtaining the GCN model, the method may include the following steps:

[0054] In step S20, a data set for training the GCN model is constructed;

[0055] In step S21, the data set is divided into a training set, a test set, and a validation set according to a ratio of 6:2:2;

[0056] In step S22, the GCN model is trained using the training set;

[0057] In step S23, the performance of the GCN model is tested using the test set;

[0058] In step S24, a validation set is used to verify whether the GCN model meets the accuracy requirements.

[0059] In this Figure 2 In the method shown, step S20 is used to construct a data set for training the GCN model. Specifically, the input of the sample of the data set can be through the collection of project attribute feature maps of completed projects. However, due to the imperfect rating of completed production projects within the power grid, it is impossible to directly read the risk level of the production project. Therefore, in one example of the present invention, it can be determined by directly obtaining the number of accidents in the completed production project. Furthermore, the number of accidents can be counted separately for different types of accidents. For example, for the failure and damage of small equipment, the number of accidents can be counted as 1, the failure and damage of medium-sized equipment, the number of accidents can be counted as 5, and for accidental injuries to personnel, the number of accidents can be counted as 10. After determining the number of accidents for each production project, the number of accidents can be divided into intervals, and finally the risk level of the production project is determined according to the result of the interval division, thereby determining the output of the sample.

[0060] In addition, when the training set is used to train the GCN model in step S22, in order to ensure the accuracy of the training, the multi-classification loss function for training the GCN model can be the following formula (1):

[0061]

[0062] Among them, L is the multi-classification loss function, n is the dimension of the item attribute feature map, and y is the output of the GCN model. is the standardized output of the GCN model, and σ is the sigmoid function.

[0063] On the other hand, the present invention also provides a multi-dimensional operation risk assessment system based on big data, the assessment system comprising a processor, the processor being configured to execute any of the assessment methods described above. Specifically, the assessment method may include the following steps:

[0064] In step S10, the personnel composition data, equipment composition data, time data, and project content data of the current project are obtained;

[0065] In step S11, a first feature graph is generated according to the personnel composition data;

[0066] In step S12, a second feature map is generated according to the device configuration data;

[0067] In step S13, a third feature map is generated according to the time data;

[0068] In step S14, a fourth feature map is generated according to the project content data;

[0069] In step S15, the first feature map, the second feature map, the third feature map and the fourth feature map are combined to obtain an item attribute feature map;

[0070] In step S16, the project attribute feature map is input into the preset GCN model to obtain the risk level of the current project.

[0071] In this Figure 1 In the evaluation method shown, step S10 is used to obtain the personnel composition data, equipment composition data, time data, and project content data of the current project. Among them, the different data characteristics of the personnel composition data, equipment composition data, time data, and project content data are taken into account. In this embodiment, the personnel composition data includes at least one of the age distribution of the personnel, whether they are temporary workers, the stability evaluation index of the personnel, the technical level, the training time, and the historical violation rate of the personnel. The equipment composition data includes at least one of the service life of the equipment, the service time of the equipment, the maintenance rate of similar equipment, the type of equipment, the danger level of the equipment, and the number of historical maintenance times of the equipment. The time data includes at least one of the project duration, the project start time, and the project end time. In addition, due to the seasonal climate distribution of the construction area, the time data can also include meteorological data. The project content data includes at least one of the type of project, the time span of the project, and the scale level of the project.

[0072] Steps S11 to S14 are used to generate the first to fourth feature graphs according to the personnel composition data, the equipment composition data, the time data, and the project content data, respectively. Considering the dimensional characteristics of the first to fourth feature graphs, in this embodiment, the process of generating the project attribute feature graph in step S15 can be to use the first feature graph as the upper left corner of the project attribute feature graph, the second feature graph as the lower left corner of the project attribute feature graph, the third feature graph as the upper right corner of the project attribute feature graph, and the fourth feature graph as the lower right corner of the project attribute feature graph to form the project attribute feature graph.

[0073] Step S16 can be used to input the project attribute feature map into a preset GCN model to obtain the risk level of the current project. The schematic diagram of the interface for generating the risk level can be as follows: Figure 2 As shown. Among them, the specific method for obtaining the GCN model can be various forms known to those skilled in the art. In one example of the present invention, the method for obtaining the GCN model can include: Figure 2 The steps shown. Figure 2 In the method for obtaining the GCN model, the method may include the following steps:

[0074] In step S20, a data set for training the GCN model is constructed;

[0075] In step S21, the data set is divided into a training set, a test set, and a validation set according to a ratio of 6:2:2;

[0076] In step S22, the GCN model is trained using the training set;

[0077] In step S23, the performance of the GCN model is tested using the test set;

[0078] In step S24, a validation set is used to verify whether the GCN model meets the accuracy requirements.

[0079] In this Figure 2 In the method shown, step S20 is used to construct a data set for training the GCN model. Specifically, the input of the sample of the data set can be through the collection of project attribute feature maps of completed projects. However, due to the imperfect rating of completed production projects within the power grid, it is impossible to directly read the risk level of the production project. Therefore, in one example of the present invention, it can be determined by directly obtaining the number of accidents in the completed production project. Furthermore, the number of accidents can be counted separately for different types of accidents. For example, for the failure and damage of small equipment, the number of accidents can be counted as 1, the failure and damage of medium-sized equipment, the number of accidents can be counted as 5, and for accidental injuries to personnel, the number of accidents can be counted as 10. After determining the number of accidents for each production project, the number of accidents can be divided into intervals, and finally the risk level of the production project is determined according to the result of the interval division, thereby determining the output of the sample.

[0080] In addition, when the training set is used to train the GCN model in step S22, in order to ensure the accuracy of the training, the multi-classification loss function for training the GCN model can be the following formula (1):

[0081]

[0082] Among them, L is the multi-classification loss function, n is the dimension of the item attribute feature map, and y is the output of the GCN model. is the standardized output of the GCN model, and σ is the sigmoid function.

[0083] In yet another aspect, the present invention further provides a computer-readable storage medium storing instructions, wherein the instructions are used to be read by a machine so as to enable the machine to execute any of the above-mentioned evaluation methods.

[0084] Through the above technical solution, the embodiment of the present invention provides a multi-dimensional operation risk assessment method and system based on big data, which constructs a project attribute feature map by acquiring personnel composition data, equipment composition data, time data, and project content data, and predicts the risk level according to the project attribute feature map through the GCN model. Compared with the prior art, the assessment method and system provided by the embodiment of the present invention achieves the accuracy of the risk level of the production project.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0090] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0091] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0092] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0093] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A multi-dimensional operation risk assessment method based on big data, characterized in that: The evaluation methods include: Obtain personnel composition data, equipment composition data, time data, and project content data of the current project; Generate a first feature graph according to the personnel composition data; generating a second feature map according to the device configuration data; generating a third feature map according to the time data; generating a fourth feature map according to the project content data; Combining the first feature map, the second feature map, the third feature map and the fourth feature map to obtain an item attribute feature map; The project attribute feature map is input into a preset GCN model to obtain the risk level of the current project.

2. The evaluation method according to claim 1, characterized in that: The personnel composition data includes at least one of the age distribution of the personnel, whether they are temporary workers, personnel stability assessment indicators, technical levels, training duration, and personnel historical violation rates.

3. The evaluation method according to claim 1, characterized in that: The equipment composition data includes at least one of equipment service life, equipment service time, maintenance rate of similar equipment, equipment type, equipment hazard level, and equipment historical maintenance times.

4. The evaluation method according to claim 1, characterized in that: The time data includes at least one of project duration, project start time, and project end time.

5. The evaluation method according to claim 1, characterized in that: The project content data includes at least one of the type of project, the time span of the project, and the scale level of the project.

6. The evaluation method according to claim 1, characterized in that: The first feature map, the second feature map, the third feature map and the fourth feature map are combined to obtain an item attribute feature map, including: Using the first feature map as the upper left corner of the project attribute feature map; Using the second feature map as the lower left corner of the item attribute feature map; Using the third feature map as the upper right corner of the project attribute feature map; The fourth feature map is used as the lower right corner of the item attribute feature map to form the item attribute feature map.

7. The evaluation method according to claim 1, characterized in that: The evaluation methods include: Constructing a dataset for training the GCN model; Divide the data set into a training set, a test set, and a validation set in a ratio of 6:2:2; Using the training set to train the GCN model; The performance of the GCN model is tested using a test set; The validation set is used to verify whether the GCN model meets the accuracy requirements.

8. The evaluation method according to claim 7, characterized in that: Using the training set to train the GCN model includes: Formula (1) is used as the multi-classification loss function of the GCN model. Wherein, L is the multi-classification loss function, n is the dimension of the item attribute feature map, and Y is the output of the GCN model. is the standardized output of the GCN model, and σ is the sigmoid function.

9. A multi-dimensional operation risk assessment system based on big data, characterized in that: The evaluation system comprises a processor, and the processor is configured to execute the evaluation method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and the instructions are used to be read by a machine so that the machine executes the evaluation method according to any one of claims 1 to 8.

Images