Electric power digital safety supervision method and related device

Abstract

The invention discloses an electric power digital safety supervision method and a related device. The method comprises the following steps: acquiring multi-dimensional environment information when an operator operates on a site; performing category feature extraction on the environment information of each dimension in the multi-dimensional environment information to obtain multiple pieces of category feature data; the association relationship among the multiple pieces of category feature data is mined, at least one target frequent item set and at least one corresponding target association degree are obtained, a single target frequent item set comprises multiple element items, and a single element item corresponds to a single piece of category feature data; determining a score of a current working environment according to multiple pieces of category feature data, the at least one target frequent item set and the at least one target association degree; and if the score of the current operation environment is greater than a preset score, starting a safety monitoring response to realize monitoring and control of the activity state of the process node of the operation site. According to the invention, the safety of field operation is guaranteed, and the efficiency of electric power safety supervision is improved.

Description

Technical Field

[0001] The present application relates to the field of electric power safety and monitoring, and in particular to an electric power digital safety and monitoring method and related devices. Background Art

[0002] With the expansion of the scale of power grids, various tasks such as power grid construction, power equipment production and operation, and equipment technology transformation have also developed vigorously. During the power production process, whether the power operation site complies with safety regulations will have a direct impact on production safety. At present, the operation monitoring of the power site is overly dependent on manual calculations, and the risk assessment is relatively arbitrary. In addition, due to the wide distribution area and large number of scattered power grid equipment, manual and scattered point monitoring takes a long time and has a large span, and cannot effectively and timely respond to various emergencies. Summary of the invention

[0003] The embodiments of the present application provide a power digital safety monitoring method and related devices to improve the efficiency of power safety monitoring.

[0004] In a first aspect, an embodiment of the present application provides a power digital safety monitoring method, including:

[0005] Obtain multi-dimensional environmental information when workers are working on site;

[0006] Extracting category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain a plurality of category feature data;

[0007] Mining the association relationship between the multiple category feature data to obtain at least one target frequent item set and at least one corresponding target association degree, wherein a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data;

[0008] Determining a score of the current working environment according to the plurality of category feature data, the at least one target frequent item set and the at least one target association degree;

[0009] If the score of the current operating environment is greater than a preset score, a safety and supervision response is initiated to monitor and control the activity status of the process nodes at the operating site.

[0010] In a second aspect, an embodiment of the present application provides a power digital safety monitoring device, including:

[0011] An acquisition unit, used to acquire multi-dimensional environmental information when operators are working on site;

[0012] An extraction unit, used to extract category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain a plurality of category feature data;

[0013] A processing unit, configured to mine the association relationship between the plurality of category feature data, obtain at least one target frequent item set and at least one corresponding target association degree, wherein a single target frequent item set includes a plurality of element items, and a single element item corresponds to a single category feature data;

[0014] a determination unit, configured to determine a score of the current operating environment according to the plurality of category feature data, the at least one target frequent item set and the at least one target association degree;

[0015] The starting unit is used to start the safety and supervision response if the score of the current working environment is greater than the preset score, so as to monitor and control the activity status of the process nodes at the working site.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing execution instructions, wherein the memory stores one or more programs; when the processor executes the execution instructions stored in the memory, the processor executes the method described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing an energy data management program, including execution instructions. When a processor of an electronic device executes the execution instructions, the processor executes the method described in the first aspect.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0019] It can be seen that in the embodiment of the present application, firstly, the multi-dimensional environmental information when the operator is working on the site is obtained; the category feature extraction is performed on the environmental information of each dimension in the multi-dimensional environmental information to obtain multiple category feature data; the association relationship between the multiple category feature data is mined to obtain at least one target frequent item set and the corresponding at least one target association degree, a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data; the score of the current working environment is determined according to the multiple category feature data, the at least one target frequent item set and the at least one target association degree; if the score of the current working environment is greater than the preset score, the safety and supervision response is initiated to realize the monitoring and control of the activity status of the process node at the working site. The present application first determines the correlation between the multi-dimensional environmental information, obtains different category feature data, and then mines the association relationship between the different category feature data, determines the feature association degree, thereby determining the on-site working environment score, realizing the intelligent early warning of the on-site working environment, thereby strengthening the management of on-site working risks, ensuring the safety of on-site working, and improving the efficiency of power safety and supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a system architecture diagram of a power digital safety monitoring system provided by an embodiment of the present application;

[0022] Figure 2 It is a flowchart of a power digital safety monitoring method provided by an embodiment of the present application;

[0023] Figure 3 This is a block diagram of the functional units of a power digital safety monitoring device provided in an embodiment of the present application;

[0024] Figure 4 This is a block diagram of the functional units of another electric power digital safety monitoring device provided in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of an electronic device proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0028] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0029] At present, the operation monitoring of power sites relies too much on manual calculations, and risk assessment is quite arbitrary. In addition, due to the wide distribution area and large number of dispersed power grid equipment, manual and scattered monitoring is time-consuming and has a large span, and cannot effectively and promptly respond to various emergencies.

[0030] In view of the above problems, an embodiment of the present application provides a power digital safety monitoring method and related devices, which are described in detail below in conjunction with the accompanying drawings.

[0031] See also Figure 1 , Figure 1 1 is a system architecture diagram of a power digital safety monitoring system provided by an embodiment of the present application. Figure 1As shown, the electric power digital safety monitoring system 100 includes a data acquisition module 101, a data preprocessing module 102, a classification module 103, a processing module 104, and an intelligent optimization module 105. The data acquisition module 101 is used to collect various on-site operation environment information, such as equipment status, environmental conditions, communication and other information, and transmit it to the data preprocessing module 102. When the data preprocessing module 102 receives the data transmitted by the data acquisition module 101, it performs relevant preprocessing operations on the data, such as processing missing values, abnormal values ​​and duplicate values, performing structural conversion and feature processing and other operations, and sends the processed data to the classification module 103. The classification module 103 classifies the data received from the data preprocessing module 102 according to the classification algorithm to obtain feature data of different categories, and The feature data of different categories are transmitted to the processing module 104. After receiving the feature data of different categories, the processing module 104 frequently processes the feature data of different categories to obtain frequent item sets, determine the feature correlation, and thus determine the on-site working environment score, quickly discover the user's behavior pattern, and be able to lock the warning behavior, thereby improving the detectability of the safety and supervision system based on association rules; the intelligent optimization module 105 is used to combine the safety and supervision data, verify the rationality of the classification algorithm according to the classification label, and update and iterate in combination with the grid parameter tuning and label distribution. At the same time, it can also obtain the safety and supervision response results and the actual warning result feedback to achieve differentiated control, and reasonably adjust the model parameters according to different application scenarios to form an effective safety and supervision result intelligent verification closed loop, and solidify the research results through the system to support practical applications.

[0032] See also Figure 2 , Figure 2 The present invention provides a method for digital power safety monitoring. The method includes the following steps.

[0033] S210, obtaining multi-dimensional environmental information of operators when they are working at the site.

[0034] Among them, multi-dimensional environmental information may include characteristic information of power grid equipment, on-site operation status information, safety-related information of operators, and operation safety and supervision information, etc. Specifically, characteristic information of power grid equipment includes basic information such as equipment type, equipment life cycle, and equipment installation location. On-site operation status information includes site size, site type, voltage conditions and other information. Safety-related information of operators includes basic information of operators such as job type and years of work, as well as information to determine whether the behavior is standardized, such as crossing the line, not wearing a safety helmet, not wearing work clothes, smoking, not carrying the correct tools, face recognition, not wearing insulating gloves, using non-insulating items near live equipment and other behavioral information. Operation safety and supervision information includes operation safety monitoring information such as whether it is strong light operation, whether it is hoisting operation, whether there is a fire extinguisher, etc.

[0035] S220, extracting category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain a plurality of category feature data.

[0036] Specifically, the method of extracting category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain multiple category feature data includes: preprocessing the multi-dimensional environmental information to obtain multi-dimensional environmental data; performing the following operations on the environmental data of each dimension in the multi-dimensional environmental data: constructing a similarity matrix according to the similarity of any two data in the environmental data; and obtaining an adjacency matrix according to the similarity matrix; and obtaining a Laplace matrix according to the adjacency matrix; and performing eigendecomposition on the Laplace matrix to obtain the first k eigenvalues ​​and eigenvectors; and classifying the first k eigenvalues ​​and the eigenvectors to obtain multiple category labels of the environmental data and category feature data corresponding to each category label in the multiple category labels.

[0037] Specifically, the preprocessing of the multidimensional environmental information to obtain multidimensional environmental data includes: performing structured processing on the multidimensional environmental information to obtain first preprocessed data; performing data cleaning and data conversion on the first preprocessed data in sequence to obtain second preprocessed data; and performing data sorting on the second preprocessed data to obtain the multidimensional environmental data.

[0038] Among them, the unstructured data in the multi-dimensional environmental information is structured to obtain the first pre-processed data, and the data is stored in the database according to the platform interface; then the first pre-processed data is cleaned and converted to obtain the second pre-processed data. Specifically, data cleaning includes deduplication and filling of redundant data, data with large missing amounts, and abnormal data. Specifically, for missing values, deletion, interpolation filling or other methods can be used for processing. Abnormal values ​​can be identified and processed by statistical methods, visualization tools or special abnormality detection algorithms. The detection and removal of duplicate values ​​can avoid the impact on the analysis results. Data conversion includes normalization, logarithmic transformation, unique hot encoding and data discretization. Specifically, corresponding feature processing is performed for different data types, such as encoding processing for character data, specific conversion of time data, and corresponding differentiation of numerical data combined with feature distribution. Then, the digitized data is normalized to make the data consistent at different scales. Specifically, the data sorting includes extracting original features and combining the original features.

[0039] Among them, data organization also includes special processing of time. For the second preprocessed data, operations such as original feature selection, creation of new features, and processing of time series data can be performed. Original feature selection helps to reduce computational complexity by combining, transforming or extracting original features to create new features. If the data contains time information, special processing of time series may be required, such as sliding windows, differences, etc.

[0040] Preprocessing can also include processing unbalanced data. To address the problem of large differences in the amount of data in different dimensions, undersampling, oversampling, or synthesizing minority category data can be used to balance the amount of data in different dimensions.

[0041] After obtaining the multi-dimensional environmental data, a similarity matrix S = [sij] is constructed according to the environmental data of different dimensions, where sij represents the similarity between point i and point j, and a similarity graph is constructed. The adjacency matrix W and degree matrix D are constructed based on the similarity matrix S through the Gaussian kernel function. The adjacency matrix W is composed of the weight values ​​w between any two points. ij The degree matrix D is a diagonal matrix, and the elements on the diagonal are the weights of the edges of the vertex. According to the adjacency matrix W and the degree matrix D, the Laplace matrix L is obtained, which is defined as L = DS. Then the Laplace matrix L is eigendecomposed, and its characteristic equation can be expressed as det(L-λI) = 0, where λ is the eigenvalue and I is the unit matrix. The above characteristic equation is solved by the power method, inverse power method or QR algorithm to obtain the eigenvalue of the Laplace matrix, and then the corresponding eigenvector is obtained by solving the linear equation system (L-λI)x = 0, where x is the eigenvector. Since the Laplace matrix may have multiple eigenvalues ​​and eigenvectors, the above steps need to be repeated until all eigenvalues ​​and eigenvectors are found. Then the first k smallest eigenvalues ​​and their corresponding eigenvectors are selected. This is because in spectral clustering, smaller eigenvalues ​​usually correspond to the main structure or community in the graph. Then, the selected feature vector is used as the column vector to construct a new feature space. A clustering algorithm is applied on this new feature space to group the data points into different clusters. Each cluster represents a community or category in the original data, and the category label of the data and the category feature data corresponding to the category label are obtained.

[0042] It can be seen that in this embodiment, the similarity matrix of the data is used to reduce the dimension by using the characteristic vector of the data, so that the characteristic data of different categories are divided in the low-dimensional space, the data of different dimensions are effectively processed, and the accurate division of the data is achieved.

[0043] S230, mining the association relationship between the plurality of category feature data to obtain at least one target frequent item set and at least one corresponding target association degree.

[0044] Among them, a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data.

[0045] Specifically, the mining of the association relationship between the plurality of category feature data to obtain at least one target frequent item set and the corresponding at least one target relevance includes: scanning the plurality of category feature data to determine the support of each data in each category feature data; performing a support threshold screening operation on the support of each data in each category feature data to obtain a plurality of first frequent item sets; performing a self-connection operation on the plurality of first frequent item sets to obtain at least one first candidate item set; determining the support of each first candidate item set in the at least one first candidate item set; performing the support threshold screening operation on each first candidate item set according to the support of each first candidate item set in the at least one first candidate item set to determine whether there is a second frequent item set; if the second frequent item set exists, repeatedly performing the self-connection operation and the support threshold screening operation until no new frequent item set can be generated; and determining the latest frequent item set obtained by performing the self-connection operation and the support threshold screening operation for the last time as the target frequent item set; obtaining the target relevance according to the target frequent item set; if the second frequent item set does not exist, determining the first frequent item set as the target frequent item set; obtaining the target relevance according to the target frequent item set.

[0046] Among them, multiple category feature data are scanned, the number of occurrences of each data is counted, and recorded as the support of the data. The above data is screened according to the preset support to obtain a frequent 1-item set, which is recorded as L1. Among them, the self-connection operation refers to selecting any two item sets from the frequent k-1 item sets found in the previous iteration, merging these two item sets into a new item set, and the new item set contains k items. Repeat the above steps until all possible combinations have been considered. Specifically, based on the multiple L1s obtained, a candidate 2-item set C2 is generated through a self-connection operation, and the entire data set is scanned again, the number of occurrences of each item in C2 is counted, and the support of C2 is obtained. The support of C2 is screened by the preset support, and the items with a support greater than the preset support are determined as frequent 2-item sets L2. Repeat the above steps until no more frequent k-item sets can be found. Finally, the frequent item sets obtained through self-join operation and support threshold screening operation are the target frequent item sets. For each target frequent item set, all possible subsets are generated and it is verified whether they meet the preset support. For each target frequent item set that meets the minimum preset support, association rules are generated and all association rules that meet the minimum confidence are output.

[0047] Among them, the relevance of the target frequent itemsets refers to support or confidence.

[0048] It can be seen that in this embodiment, through the frequent processing of feature data of different categories, all frequent item sets and association rules in the data set can be effectively mined, thereby improving the calculation efficiency, and can quickly discover the user's behavior pattern, lock the warning behavior, monitor the personnel dress code, behavior supervision, working environment, identify fireworks, abnormal equipment status, etc., to ensure the safety and controllability of the entire operation process.

[0049] S240: Determine a score of the current working environment according to the plurality of category feature data, the at least one target frequent item set, and the at least one target association degree.

[0050] Specifically, a single target frequent item set includes a first item set and a second item set, the first item set and the second item set respectively include at least one element item, the second item set is associated with the first item set, and the determining the score of the current working environment according to the multiple category feature data, the at least one target frequent item set and the at least one target association degree includes: determining the weight of each element item in each second item set according to each association degree; determining the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set; and obtaining the score of the current working environment according to the score of each first item set.

[0051] Wherein, it is assumed that the target frequent item set finally obtained is {a|bcd}, indicating that a is associated with b, c, and d, wherein the first item set is the prerequisite item set, which is {a}, and the second item set is the result item set, which is {bcd}. The association degree can be confidence or support. For example, it is assumed that the association degree is used to indicate the confidence degree, and the confidence degree of the item sets {a|b}, {a|c}, and {a|d} can be calculated respectively, and weights are assigned to b, c, and d respectively according to the confidence degree obtained above; it is assumed that the association degree is used to indicate the support degree, and the support degree of the item sets {ab}, {ac}, and {ad} can be calculated respectively, and weights are assigned to b, c, and d respectively according to the support degree obtained above. The feature data and weights corresponding to all the element items in the second item set, that is, b, c, and d, are weighted and summed to obtain the score of the first item set, that is, the score of a. Finally, according to the score and corresponding weight of each first item set, the score of the current working environment is obtained. The weight of each first item set can be determined by the confidence degree.

[0052] It can be seen that in the embodiment of the present application, by calculating the element items in the frequent item set and the corresponding feature data, the association between different data features can be effectively mined to achieve accurate confirmation of the current working environment.

[0053] Specifically, before determining the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set, the method also includes: determining the coefficient of variation of the category feature data corresponding to each element item in each first item set; determining the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set includes: determining the score of each first item set according to the weight of each element item in each second item set, the category feature data corresponding to each element item in each second item set, and the coefficient of variation of the category feature data corresponding to each element item in each first item set.

[0054] The coefficient of variation of each feature data is defined according to a specific business rule and is calculated based on the original feature data. The weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set are weighted and summed to obtain the first data value. The first data value is corrected according to the coefficient of variation to obtain the score of the first item set. Specifically, a level can be set for the coefficient of variation, and the first data value can be determined according to the level of the coefficient of variation to determine whether it is multiplied by the coefficient of variation or divided by the coefficient of variation, so as to correct the first data value and obtain the score of the first item set.

[0055] It can be seen that in this embodiment, the score of the first item set is corrected by introducing the coefficient of variation, so that the obtained score can accurately reflect the current working environment.

[0056] S250: If the score of the current operating environment is greater than a preset score, a safety and supervision response is initiated to monitor and control the activity status of the process nodes at the operating site.

[0057] Among them, the activity status includes the action status of the operator at the corresponding process node and / or the equipment operation status of the controlled equipment. The action status of the operator refers to the operating posture of the operator when performing the operation. The equipment operation status of the controlled equipment includes electrical performance, mechanical status, operating parameters and maintenance status, etc.

[0058] Among them, if the score of the current working environment is less than or equal to the preset score, it indicates that the current working environment is a safe working environment and there is no need to initiate a security response. If the score of the current working environment is greater than the preset score, it indicates that there are safety issues in the current working environment, such as workers not wearing safety helmets, smoking, and other personal safety hazards. Specifically, specific safety issues can be found based on the scores of each first set, so as to achieve accurate problem finding.

[0059] It can be seen that in the embodiment of the present application, the correlation between multi-dimensional environmental information is first determined to obtain feature data of different categories, and then the correlation between feature data of different categories is mined to determine the feature correlation degree, thereby determining the on-site working environment score and realizing intelligent early warning of the on-site working environment, thereby strengthening the management of on-site working risks, ensuring the safety of on-site operations, and improving the efficiency of power safety supervision.

[0060] For the above embodiments, please refer to Figure 3 , Figure 3 is a block diagram of the functional units of a power digital safety monitoring device provided in an embodiment of the present application, such as Figure 3 As shown, the electric power digital safety monitoring device 30 includes: an acquisition unit 31, which is used to acquire multi-dimensional environmental information when the operator is working on the site; an extraction unit 32, which is used to extract category features of the environmental information of each dimension in the multi-dimensional environmental information to obtain multiple category feature data; a processing unit 33, which is used to mine the association relationship between the multiple category feature data, obtain at least one target frequent item set and corresponding at least one target association degree, a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data; a determination unit 34, which is used to determine the score of the current working environment according to the multiple category feature data, the at least one target frequent item set and the at least one target association degree; a start unit 35, which is used to start the safety monitoring response if the score of the current working environment is greater than the preset score, so as to realize the monitoring and control of the activity status of the process node at the working site.

[0061] In a possible embodiment, a single target frequent item set includes a first item set and a second item set, the first item set and the second item set respectively include at least one element item, the second item set is associated with the first item set, and in determining the score of the current working environment according to multiple category feature data, the at least one target frequent item set and the at least one target association degree, the determination unit 34 is specifically used to: determine the weight of each element item in each second item set according to each association degree; determine the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set; and obtain the score of the current working environment according to the score of each first item set.

[0062] In a possible embodiment, before determining the score of each first item set based on the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set, the power digital safety monitoring device 30 is specifically used to: determine the coefficient of variation of the category feature data corresponding to each element item in each first item set; the determining the score of each first item set based on the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set includes: determining the score of each first item set based on the weight of each element item in each second item set, the category feature data corresponding to each element item in each second item set, and the coefficient of variation of the category feature data corresponding to each element item in each first item set.

[0063] In a possible embodiment, in terms of extracting category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain multiple category feature data, the extraction unit 32 is specifically used to: preprocess the multi-dimensional environmental information to obtain multi-dimensional environmental data; perform the following operations on the environmental data of each dimension in the multi-dimensional environmental data: construct a similarity matrix based on the similarity of any two data in the environmental data; and obtain an adjacency matrix based on the similarity matrix; and obtain a Laplace matrix based on the adjacency matrix; and perform eigendecomposition on the Laplace matrix to obtain the first k eigenvalues ​​and eigenvectors; classify the first k eigenvalues ​​and the eigenvectors to obtain multiple category labels of the environmental data and category feature data corresponding to each category label in the multiple category labels.

[0064] In a possible embodiment, in mining the association relationship between the multiple category feature data to obtain at least one target frequent item set and the corresponding at least one target association degree, the processing unit 33 is further specifically used to: scan the multiple category feature data to determine the support of each data in each category feature data; perform a support threshold screening operation on each data in each category feature data according to the support of each data in each category feature data to obtain multiple first frequent item sets; perform a self-connection operation on the multiple first frequent item sets to obtain at least one first candidate item set; determine the support of each first candidate item set in the at least one first candidate item set; and perform a self-connection operation on the multiple first frequent item sets according to the at least one first candidate item set. The support of each first candidate item set in the first candidate item sets is used to perform the support threshold screening operation on each first candidate item set to determine whether there is a second frequent item set; if the second frequent item set exists, the self-join operation and the support threshold screening operation are repeatedly performed until no new frequent item set can be generated; and the latest frequent item set obtained by the last execution of the self-join operation and the support threshold screening operation is determined as the target frequent item set; the target relevance is obtained according to the target frequent item set; if the second frequent item set does not exist, the first frequent item set is determined as the target frequent item set; and the target relevance is obtained according to the target frequent item set.

[0065] In a possible embodiment, in terms of preprocessing the multidimensional environmental information to obtain multidimensional environmental data, the extraction unit 32 is specifically used to: perform structured processing on the multidimensional environmental information to obtain first preprocessed data; perform data cleaning and data conversion on the first preprocessed data in sequence to obtain second preprocessed data; and perform data sorting on the second preprocessed data to obtain the multidimensional environmental data.

[0066] In a possible embodiment, in preprocessing the multi-dimensional environmental information to obtain the multi-dimensional environmental data, the extraction unit 32 is further specifically used for: the data sorting includes extracting original features and combining the original features.

[0067] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0068] In the case of integrated units, see Figure 4 , Figure 4 is a block diagram of the functional units of another power digital safety monitoring device provided in an embodiment of the present application, such as Figure 4As shown, the power digital safety monitoring device 30 includes: a processing module 302 and a communication module 301. The processing module 302 is used to control and manage the actions of the power digital safety monitoring device 30, for example, to execute the steps of the acquisition unit 31, the extraction unit 32, the processing unit 33, the determination unit 34 and the start unit 35, and / or to execute other processes of the technology described herein. The communication module 301 is used for the interaction between the power digital safety monitoring device 30 and other devices. Figure 4 As shown, the power digital safety monitoring device 30 may further include a storage module 303 , and the storage module 303 is used to store program codes and data of the power digital safety monitoring device 30 .

[0069] Among them, the processing module 302 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 301 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 303 can be a memory.

[0070] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above power digital safety monitoring device 30 can execute the above Figure 2 The power digital safety monitoring method shown.

[0071] See also Figure 5 , Figure 5 is a schematic diagram of the structure of an electronic device proposed in an embodiment of the present application, such as Figure 5 As shown, the electronic device 500 includes a processor 510, a memory 520, a communication interface 530 and one or more programs 521. The one or more programs 521 are stored in the memory and are configured to be executed by the processor. When the program is executed, it includes part or all of the steps of any one of the cruising range estimation methods recorded in the above method embodiments. The processor, memory and communication interface are interconnected and complete communication with each other.

[0072] The memory may be a volatile memory such as a dynamic random access memory DRAM, or a non-volatile memory such as a mechanical hard disk. The memory is used to store a set of executable program codes, and the processor is used to call the executable program codes stored in the memory, and may execute part or all of the steps of any power digital safety monitoring method recorded in the above power digital safety monitoring method embodiment.

[0073] It can be seen that the electronic device 500 described in the embodiment of the present application first obtains the multi-dimensional environmental information when the operator is working on the site; extracts the category features of the environmental information of each dimension in the multi-dimensional environmental information to obtain multiple category feature data; mines the association relationship between the multiple category feature data to obtain at least one target frequent item set and the corresponding at least one target association degree, a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data; determines the score of the current working environment according to the multiple category feature data, the at least one target frequent item set and the at least one target association degree; if the score of the current working environment is greater than the preset score, the safety and supervision response is initiated to realize the monitoring and control of the activity status of the process node at the working site. The present application first determines the correlation between the multi-dimensional environmental information, obtains different category feature data, and then mines the association relationship between the different category feature data, determines the feature association degree, thereby determining the on-site working environment score, realizing the intelligent early warning of the on-site working environment, thereby strengthening the management of on-site working risks, ensuring the safety of on-site working, and improving the efficiency of power safety and supervision.

[0074] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0075] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0076] It should be noted that, for the sake of simplicity, the aforementioned method implementations are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by the present application.

[0077] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0080] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0081] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0082] A person skilled in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0083] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A power digital safety monitoring method, characterized in that: include: Obtain multi-dimensional environmental information when workers are working on site; Extracting category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain a plurality of category feature data; Mining the association relationship between the multiple category feature data to obtain at least one target frequent item set and at least one corresponding target association degree, wherein a single target frequent item set includes multiple element items, and a single element item corresponds to a single category feature data; Determining a score of the current working environment according to the plurality of category feature data, the at least one target frequent item set and the at least one target association degree; If the score of the current operating environment is greater than a preset score, a safety and supervision response is initiated to monitor and control the activity status of the process nodes at the operating site.

2. The method according to claim 1, characterized in that A single target frequent item set includes a first item set and a second item set, the first item set and the second item set respectively include at least one element item, and the second item set is associated with the first item set. The step of determining the score of the current working environment according to the plurality of category feature data, the at least one target frequent item set and the at least one target association degree includes: Determine the weight of each element item in each second item set according to each correlation degree; Determine the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set; The score of the current operating environment is obtained according to the score of each first item set.

3. The method according to claim 2, characterized in that Before determining the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set, the method further includes: Determine the coefficient of variation of the category characteristic data corresponding to each element item in each first item set; Determining the score of each first item set according to the weight of each element item in each second item set and the category feature data corresponding to each element item in each second item set includes: The score of each first item set is determined according to the weight of each element item in each second item set, the category feature data corresponding to each element item in each second item set, and the coefficient of variation of the category feature data corresponding to each element item in each first item set.

4. The method according to claim 1, characterized in that: The extracting of category features from the environment information of each dimension in the multi-dimensional environment information to obtain a plurality of category feature data includes: Preprocessing the multi-dimensional environmental information to obtain multi-dimensional environmental data; The following operations are performed for the environmental data of each dimension in the multi-dimensional environmental data: construct a similarity matrix according to the similarity of any two data in the environmental data; and obtain an adjacency matrix according to the similarity matrix; and obtain a Laplace matrix according to the adjacency matrix; and perform eigendecomposition on the Laplace matrix to obtain the first k eigenvalues ​​and eigenvectors; classify the first k eigenvalues ​​and the eigenvectors to obtain multiple category labels of the environmental data and category feature data corresponding to each category label in the multiple category labels.

5. The method according to claim 1, characterized in that The mining of the association relationship between the plurality of category feature data to obtain at least one target frequent item set and at least one corresponding target association degree includes: Scan the plurality of category feature data to determine the support of each data in each category feature data; Performing a support threshold screening operation on each data in each category feature data according to the support of each data in each category feature data to obtain a plurality of first frequent item sets; Performing a self-join operation on the plurality of first frequent item sets to obtain at least one first candidate item set; Determine the support of each first candidate item set in the at least one first candidate item set; According to the support of each first candidate item set in the at least one first candidate item set, the support threshold screening operation is performed on each first candidate item set to determine whether there is a second frequent item set; If the second frequent itemset exists, the self-join operation and the support threshold screening operation are repeatedly performed until no new frequent itemset can be generated; and the latest frequent itemset obtained by the last execution of the self-join operation and the support threshold screening operation is determined as the target frequent itemset; and the target relevance is obtained according to the target frequent itemset; If the second frequent itemset does not exist, the first frequent itemset is determined as the target frequent itemset; and the target relevance is obtained according to the target frequent itemset.

6. The method according to claim 4, characterized in that The preprocessing of the multi-dimensional environmental information to obtain multi-dimensional environmental data includes: Performing structured processing on the multi-dimensional environmental information to obtain first pre-processed data; performing data cleaning and data conversion on the first preprocessed data in sequence to obtain second preprocessed data; The second preprocessed data is sorted to obtain the multi-dimensional environmental data.

7. The method according to claim 6, characterized in that The data sorting includes extracting original features and combining the original features.

8. A digital power safety monitoring device, characterized in that: include: An acquisition unit, used to acquire multi-dimensional environmental information when operators are working on site; An extraction unit, used to extract category features from the environmental information of each dimension in the multi-dimensional environmental information to obtain a plurality of category feature data; A processing unit, configured to mine the association relationship between the plurality of category feature data, obtain at least one target frequent item set and at least one corresponding target association degree, wherein a single target frequent item set includes a plurality of element items, and a single element item corresponds to a single category feature data; a determination unit, configured to determine a score of the current operating environment according to the plurality of category feature data, the at least one target frequent item set and the at least one target association degree; The starting unit is used to start the safety and supervision response if the score of the current working environment is greater than the preset score, so as to monitor and control the activity status of the process nodes at the working site.

9. An electronic device, characterized in that: The method comprises a processor and a memory storing execution instructions, wherein the memory stores one or more programs; when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: An energy data management program is stored, including execution instructions. When a processor of an electronic device executes the execution instructions, the processor executes the method according to any one of claims 1-7.

Images