CN117688503B - Electricity safety inspection system based on mobile terminal - Google Patents
Electricity safety inspection system based on mobile terminal Download PDFInfo
- Publication number
- CN117688503B CN117688503B CN202410155451.6A CN202410155451A CN117688503B CN 117688503 B CN117688503 B CN 117688503B CN 202410155451 A CN202410155451 A CN 202410155451A CN 117688503 B CN117688503 B CN 117688503B
- Authority
- CN
- China
- Prior art keywords
- module
- inspection
- checking
- model
- electricity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 212
- 230000005611 electricity Effects 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 230000003993 interaction Effects 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims description 49
- 230000002159 abnormal effect Effects 0.000 claims description 36
- 238000012216 screening Methods 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 7
- 238000007726 management method Methods 0.000 description 13
- 230000007246 mechanism Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of electricity management and discloses an electricity safety inspection system based on a mobile terminal. The invention realizes the whole-flow management of the electricity utilization safety inspection of the important customer at high risk through the customer interaction mobile terminal module, the customer active inspection module, the electric inspector inspection module, the supervision inspection module, the electricity utilization inspection on-line notification module and the like, improves the quality and efficiency of the inspection and meets the requirements of an electric supervision department; the intelligent analysis and matching of the state data of the electric equipment are realized through the electric safety search module, the existing electric safety hidden danger is found out, the hidden danger results are ordered, the importance is highlighted, the clients are reminded to process in time, and the safety risk of marketing field operation is reduced.
Description
Technical Field
The invention relates to the technical field of electricity management, in particular to an electricity safety inspection system based on a mobile terminal.
Background
With the importance of electricity safety management, the method is more and more important for realizing the fine management of the electricity safety of important customers with high endangerment. At present, the electricity utilization inspection function is relatively single, the working requirement cannot be met, the informationized supporting capability needs to be improved, a new mode of customer electricity utilization security inspection needs to be researched, and a management system of a customer electricity utilization inspection early warning mechanism, a work order mechanism and an interaction mechanism is constructed.
In improving the customer electricity safety management, three main problems are faced:
firstly, the external supervision of electricity safety tends to be tight and thin. The power supervision department is required to strengthen daily electricity management for high-risk important clients, so that the user, in particular to the high-risk important clients, electricity safety fine management is realized;
secondly, marketing field operation risk management and control difficulty is big. Along with the successive expansion of new marketing services, the complexity of key services is continuously deepened, the influence degree is enlarged, and the management and control difficulty of the safety risks of the operation on the marketing site is increased;
thirdly, the informatization supporting capability of the electric inspection is insufficient. The electricity inspection function of the marketing system is relatively single, and the comprehensive supervision, real-time diagnosis and treatment means are lacked, so that a new customer electricity inspection mode needs to be established.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
In view of the foregoing, an objective of the embodiments of the present application is to provide an electric safety inspection system based on a mobile terminal, so as to overcome the above-mentioned technical problems of the related art.
For this purpose, the invention adopts the following specific technical scheme:
the utility model provides an electricity safety inspection system based on remove end, this electricity safety inspection system based on remove end includes customer interactive remove end module, customer initiative inspection module, electric power inspector inspection module, supervision inspection module, electricity inspection on-line notification module and electricity safety search module.
The customer interaction mobile terminal module is used for information exchange among customers, power inspectors and monitoring staff.
The client active checking module is used for automatically triggering the checking work orders according to the checking period of the client and pushing the checking work orders to the client interactive mobile terminal module, and the client performs autonomous checking on corresponding equipment checking items and checks the check orders within a limited period.
And the electric power inspector checking module is used for receiving the inspection work orders by the electric power inspectors, checking according to the inspection items and the inspection point items, recording hidden danger conditions and generating the inspection work orders and hidden danger lists.
And the supervision and inspection module is used for supervising and checking the inspection conditions of the high-risk important clients by using supervision staff.
And the power utilization inspection on-line notification module is used for periodically inspecting by a power inspector and automatically generating a customer inspection notification.
And the electricity utilization safety search module is used for finding out existing potential safety hazards according to the state data of the electric equipment and sequencing the results of the potential safety hazards.
Optionally, the client active checking module comprises a classification labeling module, an instruction generating module and a communication module;
the classification labeling module is used for classifying and labeling the electric equipment according to the type and the application of the electric equipment;
the instruction generation module is used for generating a corresponding inspection work order according to the inspection requirement and pushing the inspection work order to the client interaction mobile terminal module;
and the communication module is used for communicating the client interaction mobile terminal module with the electric equipment to acquire the state data of the electric equipment.
Optionally, in order to intelligently analyze and match the state data of the electric equipment, the existing potential safety hazard of electricity consumption is found out:
the electricity utilization safety search module comprises a hidden danger search module and a result sequence adjustment module;
the hidden danger searching module is used for analyzing and matching the state data according to the data type and the semantic dimension, and finding out the existing potential safety hazards of electricity consumption to obtain a checking result;
and the result sequence adjusting module is used for sequencing the inspection results so that the difference between the adjacent inspection results is larger.
Optionally, the hidden danger searching module comprises a clustering module, a semantic analysis module, a matching module and a hidden danger identifying module;
the clustering module is used for clustering the state data of the electric equipment and obtaining a data type clustering result;
the semantic analysis module is used for carrying out semantic analysis on the state data, extracting the meaning of the state data, and clustering the state data again to obtain a semantic clustering result;
the matching module is used for analyzing the data type and the semantics of the instruction in the inspection work order, respectively finding out the data type category and the semantic category which are the same as the instruction in the state data, and simultaneously determining the intersection of the data type category and the semantic category in the state data as matched state data;
and the hidden danger identification module is used for analyzing whether the potential safety hazards exist according to the matched state data, and marking the potential safety hazards as the potential safety hazards if the potential safety hazards exist.
According to the matched state data, analyzing whether the potential safety hazard of electricity consumption exists or not comprises the following steps:
the method comprises the steps of primarily dividing collected matched state data into a training set A only containing normal state samples, a training set B containing normal and abnormal state samples and a testing set C containing normal and abnormal state samples, and cross-dividing the training set A into a plurality of training subsets;
training a random forest model by using each training subset, obtaining a set of a plurality of screening models, calculating the average height of each tree of each training subset in the screening models of the samples, obtaining an abnormal score, and setting an abnormal score threshold according to the abnormal score;
carrying each sample in the training set B into each screening model to calculate an abnormal score, if the abnormal score of the sample exceeds an abnormal score threshold value, voting the sample by the screening model to represent abnormality, otherwise, not voting, and counting the total number of votes obtained by each sample in the training set B;
and taking the minimum value of the ticket number obtained by the abnormal sample in the training set B as an abnormal detection threshold, and carrying out preliminary identification on the sample in the training set B according to the abnormal detection threshold and the ticket obtaining condition of the sample, namely, if the ticket obtaining number of the sample reaches or exceeds the abnormal detection threshold, primarily identifying as abnormal. The method comprises the steps of carrying out a first treatment on the surface of the
Training a support vector machine model by using a sample and a linear kernel function which are initially identified as abnormal, so as to obtain a prediction model for identifying potential safety hazards of electricity consumption;
evaluating the performance of each of the screening model and the predictive model using an independent test set;
and analyzing the new matched state data through the trained screening model and the prediction model, and identifying potential safety hazards.
Optionally, to increase the diversity of inspection results, avoiding duplicate or similar results from taking up excessive space, thereby increasing the efficiency and coverage of the inspection; the importance of the inspection result can be highlighted, and the customers can more easily notice the existing potential safety hazards of electricity consumption, so that the quality and the safety of inspection are improved:
the result sequence adjusting module comprises a similarity calculating module and a sequencing module;
the similarity calculation module is used for calculating the similarity between each checking result and other checking results according to the data type and semantic analysis;
and the sequencing module is used for sequencing all the inspection results.
Optionally, when sorting all the inspection results, scoring all the inspection results, and sorting all the inspection results from high to low according to the scores to obtain an initial inspection result list.
Optionally, after obtaining an initial inspection result list, sequentially taking out the two inspection results with the highest scores and the lowest scores from the initial inspection result list, putting the two inspection results into a new inspection result list, repeating until the initial inspection result list is empty, and outputting the new inspection result list at the same time, wherein the scores of adjacent inspection results in the list are larger.
Alternatively, when all the inspection results are scored, the scoring is performed according to the importance of the inspection results, and the higher the importance, the higher the score.
Optionally, when scoring all the inspection results, scoring the inspection results by using a scoring model;
the method comprises the steps of taking the data types and semantic analysis results in the scored inspection results as input features, taking importance scores of the scored inspection results as output tags, and constructing a training data set and a testing data set;
training a scoring model by using a training data set and a least square method, and calculating an optimal regression coefficient;
evaluating the performance of the scoring model using the test dataset, calculating a difference between the predicted score and the actual score;
the new inspection result is subjected to importance scoring output through the trained scoring model;
and constructing a corresponding scoring sub-model for each electric safety inspection item, and selecting a corresponding sub-model for prediction according to the inspection item of the new inspection when predicting the importance score of the new inspection result. .
Optionally, after training, the scoring model is evaluated by using a test data set, an evaluation index of the model is calculated, and the generalization capability and stability of the model are checked.
Embodiments of the present invention include the following beneficial effects:
(1) According to the mobile-end-based electricity safety inspection system, through the client interaction mobile-end module, the client active inspection module, the electric inspector inspection module, the supervision inspection module, the electricity inspection on-line notification module and the like, the whole-flow management of electricity safety inspection of important clients at high risk is realized, the quality and the timeliness of inspection are improved, and the requirements of an electric supervision department are met;
(2) The invention can reduce the risk management and control difficulty of marketing field operation, realize the intelligent analysis and matching of the state data of the electric equipment through the electric safety search module, find out the potential electric safety hazards, order the results of the potential hazards, highlight the importance, remind customers to process in time, and reduce the safety risk of marketing field operation;
(3) The invention enhances the informatization supporting capability of the electricity utilization inspection, realizes informatization processing of the type and the purpose of electric equipment, inspection requirements, state data, data types, semantics, inspection results and the like through a classification marking module, an instruction generating module, a communication module, a clustering module, a semantic analysis module, a matching module, a hidden danger identification module, a similarity calculation module, a scoring module and the like, improves the inspection efficiency and accuracy, and establishes a new customer electricity utilization security inspection mode; meanwhile, the data type and the semantic analysis result of the scored inspection result are used as input features, so that the key information of the inspection result can be captured, and the prediction capability of the model can be improved. The new inspection results are subjected to importance scoring through the trained scoring model, so that the problems needing to be processed preferentially can be identified quickly, corresponding scoring sub-models are built for each electric safety inspection item, scoring can be performed more accurately for different inspection items, and the accuracy and applicability of scoring are improved;
(4) The invention uses the screening model to carry out preliminary screening, can rapidly identify the abnormal sample in the possible electricity safety inspection data, and reduces the data quantity required to be processed in the subsequent step; the abnormal detection threshold value is determined through a voting mechanism, so that the stability and reliability of hidden danger identification are improved; the final prediction is carried out by using the prediction model, so that a more accurate classification result can be provided, and the existing potential safety hazards of electricity can be found.
Drawings
For a clearer description of an embodiment of the present invention or a technical solution in the prior art, the drawings that need to be used in the embodiment will be briefly described, it will be apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person of ordinary skill in the art;
FIG. 1 is a functional block diagram of a mobile-based electrical security inspection system in accordance with an embodiment of the present invention;
in the figure:
1. a client interaction mobile terminal module; 2. a client active checking module; 3. a power inspector inspection module; 4. a supervision and inspection module; 5. an on-line notification module for power utilization inspection; 6. and the electricity utilization safety searching module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
According to an embodiment of the invention, an electric safety inspection system based on a mobile terminal is provided.
Referring to the drawings and the detailed description, as shown in fig. 1, the mobile-end-based electricity safety inspection system according to the embodiment of the invention includes a client interaction mobile-end module 1, a client active inspection module 2, an electric inspector inspection module 3, a supervision inspection module 4, an on-line notification module 5 and an electricity safety search module 6.
The customer interaction mobile terminal module 1 is used for information exchange of customers, electric power inspectors and monitoring staff, and comprises inspection assistance, safety problems, inspection complaints and the like, wherein three-party linkage improves inspection quality, and communication comprises one-to-one communication, three-party communication and the like; the client interaction mobile terminal module can adopt a mobile application program (App) or a Web application program (Web App) and the like;
the client active checking module 2 is used for automatically triggering the checking work orders according to the checking period of the client and pushing the checking work orders to the client interactive mobile terminal module, and the client performs automatic checking on corresponding equipment checking items and checks the check orders within a limited period.
In a further embodiment, the client active inspection module 2 comprises a classification labeling module, an instruction generating module and a communication module;
the classification labeling module is used for classifying and labeling the electric equipment according to the type and the application of the electric equipment;
the instruction generation module is used for generating a corresponding inspection work order according to the inspection requirement and pushing the inspection work order to the client interaction mobile terminal module;
and the communication module is used for communicating the client interaction mobile terminal module with the electric equipment to acquire the state data of the electric equipment.
And the electric power inspector checking module 3 is used for receiving the inspection work orders by the electric power inspectors, checking according to the inspection items and the inspection point items, recording hidden danger conditions and generating the inspection work orders and hidden danger lists.
The supervision and inspection module 4 is used for supervising and checking the inspection conditions of the high-risk important clients by a supervisor; important users who give questions to users or do not self-check or do not check periodically for a long time can initiate joint check, and government supervisory personnel, electricity utilization check personnel and clients can jointly carry out on-site solution to the problems of the clients and carry out on-site check.
And the electricity inspection on-line notification module 5 is used for periodically inspecting by an electricity inspector, automatically generating a customer inspection notification sheet, and viewing, downloading and the like by a customer, and viewing and processing hidden danger information by the customer.
And the electricity utilization safety search module 6 is used for finding out existing potential electricity utilization safety hazards according to the state data of the electric equipment and sequencing the results of the potential electricity utilization hazards.
In a further embodiment, the electricity consumption safety search module 6 comprises a hidden danger searching module and a result sequence adjusting module;
the hidden danger searching module is used for analyzing and matching the state data according to the data type and the semantic dimension, and finding out the existing potential safety hazards of electricity consumption to obtain a checking result;
and the result sequence adjusting module is used for sequencing the inspection results so that the difference between the adjacent inspection results is larger.
In a further embodiment, the hidden danger searching module comprises a clustering module, a semantic analysis module, a matching module and a hidden danger identification module;
the clustering module is used for clustering the state data of the electric equipment and obtaining a data type clustering result.
The semantic analysis module is used for carrying out semantic analysis on the state data, extracting the meaning of the state data, and clustering the state data again to obtain a semantic clustering result.
In addition, for data type clustering, a distance-based clustering method, such as a K-means algorithm, is used, distances between data are calculated according to numerical characteristics of state data of electric equipment, and data with similar distances are divided into the same category, so that a data type clustering result is obtained.
For semantic clustering, a text-based clustering method, such as a topic model, a word embedding model and the like, is used, semantic information of data is extracted according to text features of state data of electric equipment, and data with similar semantics are divided into the same category, so that a semantic clustering result is obtained.
The matching module is used for analyzing the data type and the semantics of the instruction in the inspection work order, respectively finding out the data type category and the semantic category which are the same as the instruction in the state data, and simultaneously determining the intersection of the data type category and the semantic category in the state data as matched state data.
And the hidden danger identification module is used for analyzing whether the potential safety hazards exist according to the matched state data, and marking the potential safety hazards as the potential safety hazards if the potential safety hazards exist.
According to the matched state data, analyzing whether the potential safety hazard of electricity consumption exists or not comprises the following steps:
the collected matched state data is primarily divided into a training set A only containing normal state samples, a training set B containing normal and abnormal state samples and a testing set C containing normal and abnormal state samples, and the training set A is divided into a plurality of training subsets in a crossing manner.
Training a random forest model by using each training subset, obtaining a set of a plurality of screening models, calculating the average height of each tree of each training subset in the screening models of the samples, obtaining an anomaly score, and setting an anomaly score threshold according to the anomaly score.
And (3) carrying each sample in the training set B into each screening model to calculate an abnormality score, if the abnormality score of the sample exceeds an abnormality score threshold, voting the sample by the screening model to represent abnormality, otherwise, not voting, and counting the total number of votes obtained by each sample in the training set B.
And taking the minimum value of the ticket number obtained by the abnormal sample in the training set B as an abnormal detection threshold, and carrying out preliminary identification on the sample in the training set B according to the abnormal detection threshold and the ticket obtaining condition of the sample.
And training a support vector machine model by using the samples which are initially identified as abnormal and the linear kernel function to obtain a prediction model for identifying the potential safety hazards of electricity.
The performance of each of the screening model and the predictive model is evaluated using separate test sets, and parameters are adjusted to optimize the model.
And analyzing the new matched state data through the trained screening model and the prediction model, and identifying potential safety hazards.
In a further embodiment, the result sequence adjustment module includes a similarity calculation module and a ranking module;
the similarity calculation module is configured to calculate, for each inspection result, the similarity between the inspection result and other inspection results according to the data type and the semantic analysis, and may use methods such as cosine similarity and euclidean distance. Cosine similarity is a cosine value for measuring the included angle of two vectors, and the closer the value is to 1, the more similar the two vectors are; the euclidean distance is a measure of the distance between two vectors, the smaller the value, the more similar the two vectors are.
And the sequencing module is used for sequencing all the inspection results.
In a further embodiment, when sorting all inspection results, scoring all inspection results, and sorting all inspection results from high to low according to scores, an initial list of inspection results is obtained.
In a further embodiment, after an initial list of inspection results is obtained, the two inspection results with the highest scores and the lowest scores are sequentially taken out of the initial list of inspection results, placed in a new list of inspection results, and repeated until the initial list of inspection results is empty, and a new list of inspection results is output, wherein the scores between adjacent inspection results in the list are larger.
In addition, through the sequencing module, the diversity of the inspection results is improved, and repeated or similar results are prevented from occupying excessive space, so that the inspection efficiency and coverage rate are improved; the importance of the inspection result can be highlighted, and the customer can more easily notice the existing potential safety hazard of electricity consumption, so that the quality and the safety of inspection are improved.
In a further embodiment, all inspection results are scored according to the importance of the inspection results, and the higher the importance, the higher the score.
In a further embodiment, the scoring model is used to score the inspection results when scoring all inspection results.
The method comprises the steps of taking the data types and semantic analysis results in the scored checking results as input features, taking importance scores of the scored checking results as output labels, and constructing a training data set and a testing data set.
Selecting a linear regression model as a scoring model, and training the scoring model by using a training data set and a least square method to calculate an optimal regression coefficient;
evaluating the performance of the scoring model using a test dataset, calculating the difference between the predicted score and the actual score, using an indicator such as Mean Square Error (MSE), root Mean Square Error (RMSE), or decision coefficient (R < chi >); returning to a scoring model training link for adjustment according to the scoring model evaluation result so as to improve the prediction accuracy of the model;
the new inspection result is subjected to importance scoring output through the trained scoring model;
and constructing a corresponding scoring sub-model for each electric safety inspection item, and selecting a corresponding sub-model for prediction according to the inspection item of the new inspection when predicting the importance score of the new inspection result.
In a further embodiment, after training, the scoring model is evaluated using a test data set, and evaluation indexes of the model, such as mean square error, accuracy, recall, and the like, are calculated to verify the generalization ability and stability of the model.
Specifically, according to the result of the evaluation index, the scoring model is optimized or adjusted, and methods such as cross verification, grid search, feature selection and the like can be used for improving the performance of the model and improving the accuracy and reliability of the model.
When the system is specifically used, a client, a power inspector and a supervisor download and install a mobile terminal application or access a Web application, create an account and log in the system. The user configures personal information according to roles (clients, inspectors, supervisors);
automatically triggering an inspection work order according to a set inspection period, pushing the inspection work order to a mobile terminal of a client, automatically inspecting designated equipment according to an inspection item after the client receives a notification, and uploading an inspection result;
the inspector receives the inspection work orders distributed by the system, goes to the site or remotely to inspect according to the inspection items and the inspection points, and records hidden danger; after completion, generating an inspection work list and a hidden danger list, and uploading the inspection work list and the hidden danger list to a system;
the supervision staff supervises and checks the checking condition and hidden danger through the mobile terminal module, and the supervision staff can audit and feed back the checking process and result;
automatically generating a client inspection notice according to the periodic inspection of the electric power inspector, and enabling the client to know upcoming inspection arrangement after receiving the inspection notice;
the potential electricity utilization potential safety hazards are intelligently found out through state data analysis of the electric equipment, the hidden danger results are ordered by the system, and related personnel are notified through the mobile terminal module;
according to hidden danger information provided by the system, a client or an inspector takes corresponding measures to carry out hidden danger correction, and after correction is completed, related information is updated into the system so as to facilitate follow-up tracking and auditing.
In summary, according to the mobile-end-based electricity safety inspection system provided by the invention, through the client interaction mobile-end module 1, the client active inspection module 2, the electric power inspector inspection module 3, the supervision inspection module 4, the electricity inspection on-line notification module 5 and the like, the whole process management of electricity safety inspection of important clients at high risk is realized, the quality and timeliness of inspection are improved, and the requirements of an electric power supervision department are met. According to the invention, the risk management and control difficulty of marketing field operation can be reduced, the intelligent analysis and matching of the state data of the electric equipment are realized through the electric safety search module 6, the existing electric safety hidden danger is found, the hidden danger results are ordered, the importance is highlighted, the clients are reminded to process in time, and the safety risk of the marketing field operation is reduced. The invention enhances the informatization supporting capability of the electricity utilization inspection, realizes informatization processing of the type and the purpose of electric equipment, inspection requirements, state data, data types, semantics, inspection results and the like through a classification marking module, an instruction generating module, a communication module, a clustering module, a semantic analysis module, a matching module, a hidden danger identification module, a similarity calculation module, a scoring module and the like, improves the inspection efficiency and accuracy, and establishes a new customer electricity utilization security inspection mode. Meanwhile, the data type and the semantic analysis result of the scored inspection result are used as input features, so that the key information of the inspection result can be captured, and the prediction capability of the model can be improved. The new inspection results are scored in importance through the trained scoring model, so that the problems needing to be processed preferentially can be identified quickly, corresponding scoring sub-models are built for each electric safety inspection item, scoring can be carried out more accurately on different inspection items, and scoring accuracy and applicability are improved. The invention uses the screening model to carry out preliminary screening, can rapidly identify the abnormal sample in the possible electricity safety inspection data, and reduces the data quantity required to be processed in the subsequent step; the abnormal detection threshold value is determined through a voting mechanism, so that the stability and reliability of hidden danger identification are improved; the final prediction is carried out by using the prediction model, so that a more accurate classification result can be provided, and the existing potential safety hazards of electricity can be found.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional charging modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (8)
1. The system is characterized by comprising a client interaction mobile terminal module, a client active checking module, an electric inspector checking module, a supervision checking module, an electric inspection on-line notification module and an electric safety searching module;
the customer interaction mobile terminal module is used for information exchange among customers, power inspectors and monitoring staff;
the client active checking module is used for automatically triggering the checking work orders according to the checking period of the client and pushing the checking work orders to the client interactive mobile terminal module, and the client performs automatic checking on corresponding equipment checking items and checks the check orders within a limited period;
the electric power inspector checking module is used for receiving the checking work orders by the electric power inspectors, checking according to the checking items and the checking point items, recording hidden danger conditions and generating the checking work orders and hidden danger lists;
the supervision and inspection module is used for supervising and checking the inspection conditions of the high-risk important clients by a supervisor;
the on-line notification module of the electricity inspection is used for periodically inspecting by an electricity inspector and automatically generating a customer inspection notification;
the electricity utilization safety search module is used for finding out existing potential safety hazards according to state data of electric equipment and sequencing results of the potential safety hazards;
the electricity utilization safety search module comprises a hidden danger search module and a result sequence adjustment module; the hidden danger searching module is used for analyzing and matching the state data according to the data type and the semantic dimension, finding out existing potential safety hazards of electricity and obtaining a checking result; the result sequence adjusting module is used for sequencing the inspection results so that the difference between the adjacent inspection results is larger;
the hidden danger searching module comprises a clustering module, a semantic analysis module, a matching module and a hidden danger identification module; the clustering module is used for clustering the state data of the electric equipment and obtaining a data type clustering result; the semantic analysis module is used for carrying out semantic analysis on the state data, extracting the meaning of the state data, and clustering the state data again to obtain a semantic clustering result; the matching module is used for analyzing the data type and the semantic of the instruction in the inspection work order, respectively finding out the data type category and the semantic category which are the same as the instruction in the state data, and simultaneously determining the intersection of the data type category and the semantic category in the state data as matched state data; the hidden danger identification module is used for analyzing whether the potential safety hazards exist according to the matched state data, and if so, marking the potential safety hazards as potential safety hazards;
according to the matched state data, analyzing whether the potential safety hazard of electricity consumption exists or not comprises the following steps:
the method comprises the steps of primarily dividing collected matched state data into a training set A only containing normal state samples, a training set B containing normal and abnormal state samples and a testing set C containing normal and abnormal state samples, and cross-dividing the training set A into a plurality of training subsets;
training a random forest model by using each training subset, obtaining a set of a plurality of screening models, calculating the average height of each tree of each training subset in the screening models of the samples, obtaining an abnormal score, and setting an abnormal score threshold according to the abnormal score;
carrying each sample in the training set B into each screening model to calculate an abnormal score, if the abnormal score of the sample exceeds an abnormal score threshold value, voting the sample by the screening model to represent abnormality, otherwise, not voting, and counting the total number of votes obtained by each sample in the training set B;
taking the minimum value of the ticket number obtained by the abnormal sample in the training set B as an abnormal detection threshold, and carrying out preliminary identification on the sample in the training set B according to the abnormal detection threshold and the ticket obtaining condition of the sample;
training a support vector machine model by using a sample and a linear kernel function which are initially identified as abnormal, so as to obtain a prediction model for identifying potential safety hazards of electricity consumption;
evaluating the performance of each of the screening model and the predictive model using an independent test set;
and analyzing the new matched state data through the trained screening model and the prediction model, and identifying potential safety hazards.
2. The mobile-terminal-based electricity safety inspection system according to claim 1, wherein the customer active inspection module comprises a classification labeling module, an instruction generation module and a communication module;
the classification labeling module is used for classifying and labeling the electric equipment according to the type and the application of the electric equipment;
the instruction generation module is used for generating a corresponding inspection work order according to the inspection requirement and pushing the inspection work order to the client interaction mobile terminal module;
the communication module is used for communicating the customer interaction mobile terminal module with the electric equipment and obtaining the state data of the electric equipment.
3. The mobile-terminal-based electricity safety inspection system according to claim 1, wherein the result sequence adjustment module comprises a similarity calculation module and a sequencing module;
the similarity calculation module is used for calculating the similarity between each checking result and other checking results according to the data type and semantic analysis;
the sorting module is used for sorting all the inspection results.
4. A mobile-terminal-based electricity safety inspection system according to claim 3, wherein when all inspection results are ranked, all inspection results are scored, and all inspection results are ranked from high to low according to the score, so as to obtain an initial inspection result list.
5. The mobile-based electrical safety inspection system according to claim 4, wherein after an initial inspection result list is obtained, two inspection results with highest scores and lowest scores are sequentially taken out from the initial inspection result list, and are put into a new inspection result list, and repeated until the initial inspection result list is empty, and a new inspection result list is output, wherein the scores between adjacent inspection results in the list are larger.
6. The mobile-based electrical safety inspection system according to claim 4, wherein when all inspection results are scored, the scoring is performed according to the importance of the inspection results, and the higher the importance is, the higher the scoring is.
7. The mobile-terminal-based electricity safety inspection system according to claim 6, wherein when all inspection results are scored, the scoring model is used for scoring the inspection results;
the method comprises the steps of taking the data types and semantic analysis results in the scored inspection results as input features, taking importance scores of the scored inspection results as output tags, and constructing a training data set and a testing data set;
training a scoring model by using a training data set and a least square method, and calculating an optimal regression coefficient;
evaluating the performance of the scoring model using the test dataset, calculating a difference between the predicted score and the actual score;
the new inspection result is subjected to importance scoring output through the trained scoring model;
and constructing a corresponding scoring sub-model for each electric safety inspection item, and selecting a corresponding sub-model for prediction according to the inspection item of the new inspection when predicting the importance score of the new inspection result.
8. The mobile-end-based electrical safety inspection system according to claim 7, wherein the scoring model is evaluated by using a test data set after training, and an evaluation index of the model is calculated to verify generalization ability and stability of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410155451.6A CN117688503B (en) | 2024-02-04 | 2024-02-04 | Electricity safety inspection system based on mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410155451.6A CN117688503B (en) | 2024-02-04 | 2024-02-04 | Electricity safety inspection system based on mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117688503A CN117688503A (en) | 2024-03-12 |
| CN117688503B true CN117688503B (en) | 2024-04-16 |
Family
ID=90137561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410155451.6A Active CN117688503B (en) | 2024-02-04 | 2024-02-04 | Electricity safety inspection system based on mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117688503B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853439A (en) * | 2010-05-06 | 2010-10-06 | 安徽省电力公司合肥供电公司 | Movable electrical inspection application system |
| CN104301406A (en) * | 2014-10-09 | 2015-01-21 | 国家电网公司 | Mobile operation terminal platform and access method based on marketing system and acquisition system |
| CN105704130A (en) * | 2016-01-29 | 2016-06-22 | 国网山东省电力公司荣成市供电公司 | Electricity safety system based on wireless communication devices |
| CN109214769A (en) * | 2018-07-11 | 2019-01-15 | 国网上海市电力公司 | A kind of network interaction platform for power grid supervision of power consumption |
| CN112633695A (en) * | 2020-12-24 | 2021-04-09 | 北京首都国际机场股份有限公司 | Intelligent safety management system |
| CN113095633A (en) * | 2021-03-23 | 2021-07-09 | 同望科技股份有限公司 | Engineering project construction site potential safety hazard investigation system based on componentization |
| CN113642856A (en) * | 2021-07-27 | 2021-11-12 | 杨道合 | Accident prevention and hidden danger investigation interactive management method |
| CN113807602A (en) * | 2021-09-29 | 2021-12-17 | 国网新源控股有限公司 | Safety risk management and control and hidden danger supervision and early warning system for pumped storage power station |
| CN115114448A (en) * | 2022-06-02 | 2022-09-27 | 中国电力科学研究院有限公司 | Intelligent multi-mode fusion electricity utilization inspection method, device, system, equipment and medium |
| CN116402344A (en) * | 2023-03-27 | 2023-07-07 | 厦门市政智慧城市科技有限公司 | Safety management platform |
| CN116938507A (en) * | 2023-03-15 | 2023-10-24 | 国网河北省电力有限公司电力科学研究院 | Electric power internet of things security defense terminal and control system thereof |
| CN117115728A (en) * | 2023-07-13 | 2023-11-24 | 国网甘肃省电力公司 | Risk identification method and system applied to field operation of transformer substation |
-
2024
- 2024-02-04 CN CN202410155451.6A patent/CN117688503B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853439A (en) * | 2010-05-06 | 2010-10-06 | 安徽省电力公司合肥供电公司 | Movable electrical inspection application system |
| CN104301406A (en) * | 2014-10-09 | 2015-01-21 | 国家电网公司 | Mobile operation terminal platform and access method based on marketing system and acquisition system |
| CN105704130A (en) * | 2016-01-29 | 2016-06-22 | 国网山东省电力公司荣成市供电公司 | Electricity safety system based on wireless communication devices |
| CN109214769A (en) * | 2018-07-11 | 2019-01-15 | 国网上海市电力公司 | A kind of network interaction platform for power grid supervision of power consumption |
| CN112633695A (en) * | 2020-12-24 | 2021-04-09 | 北京首都国际机场股份有限公司 | Intelligent safety management system |
| CN113095633A (en) * | 2021-03-23 | 2021-07-09 | 同望科技股份有限公司 | Engineering project construction site potential safety hazard investigation system based on componentization |
| CN113642856A (en) * | 2021-07-27 | 2021-11-12 | 杨道合 | Accident prevention and hidden danger investigation interactive management method |
| CN113807602A (en) * | 2021-09-29 | 2021-12-17 | 国网新源控股有限公司 | Safety risk management and control and hidden danger supervision and early warning system for pumped storage power station |
| CN115114448A (en) * | 2022-06-02 | 2022-09-27 | 中国电力科学研究院有限公司 | Intelligent multi-mode fusion electricity utilization inspection method, device, system, equipment and medium |
| CN116938507A (en) * | 2023-03-15 | 2023-10-24 | 国网河北省电力有限公司电力科学研究院 | Electric power internet of things security defense terminal and control system thereof |
| CN116402344A (en) * | 2023-03-27 | 2023-07-07 | 厦门市政智慧城市科技有限公司 | Safety management platform |
| CN117115728A (en) * | 2023-07-13 | 2023-11-24 | 国网甘肃省电力公司 | Risk identification method and system applied to field operation of transformer substation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117688503A (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20140309989A1 (en) | Method and system for analyzing text | |
| Nkonyana et al. | Performance evaluation of data mining techniques in steel manufacturing industry | |
| CN105373894A (en) | Inspection data-based power marketing service diagnosis model establishing method and system | |
| CN110319982A (en) | Underground gas pipeline leak judgment method based on machine learning | |
| CN104200288A (en) | Equipment fault prediction method based on factor-event correlation recognition | |
| CN109633518A (en) | A kind of intelligent electric energy meter comprehensive performance evaluation method, apparatus | |
| CN110765268A (en) | Client appeal-based accurate distribution network investment strategy method | |
| CN116596305A (en) | Risk grading method for food safety management | |
| CN115660262A (en) | Intelligent engineering quality inspection method, system and medium based on database application | |
| CN117076521A (en) | Operational data analysis method and system based on big data | |
| CN116542800A (en) | Intelligent financial statement analysis system based on cloud AI technology | |
| CN118297444A (en) | Artificial intelligence-oriented data set quality general assessment method | |
| CN113392920B (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN116862209B (en) | New energy automobile charging facility management method and system | |
| CN114118793A (en) | Local exchange risk early warning method, device and equipment | |
| CN117007977B (en) | Energy storage battery health state diagnosis method | |
| CN113435753A (en) | Enterprise risk judgment method, device, equipment and medium in high-risk industry | |
| CN117688503B (en) | Electricity safety inspection system based on mobile terminal | |
| CN108258802B (en) | Method and device for monitoring running condition of power distribution equipment in power distribution network | |
| CN116189896B (en) | Cloud-based diabetes health data early warning method and system | |
| CN117172721A (en) | Data flow supervision early warning method and system for financing service | |
| CN114726096B (en) | Emergency command centralized control system and monitoring method in intelligent power grid based on IMS | |
| CN113377640B (en) | Method, medium, device and computing equipment for explaining model under business scene | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| CN112784080B (en) | Scene recommendation method, system and device based on three-dimensional digital platform of power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |