Power utilization inspection full-process work quality and efficiency evaluation system based on big data

Abstract

The invention relates to the technical field of power system detection, in particular to a big data-based power utilization inspection whole-process work quality and efficiency evaluation system, which comprises a data acquisition module, an index system construction module, an evaluation model construction module, an evaluation analysis module and a result output module, the data acquisition module is used for collecting multi-source data in power utilization inspection work; the index system construction module is used for constructing a power utilization inspection whole-process work quality and efficiency evaluation system; the evaluation model construction module is used for constructing a power utilization inspection whole-process work quality and efficiency evaluation model; the evaluation and analysis module inputs the preprocessed data into an evaluation model for calculation and analysis to obtain a quality-effect evaluation result; and the result output module is used for displaying and outputting the evaluation result. Through cooperation of multiple modules, comprehensive data acquisition and scientific construction of indexes and models, power utilization inspection work is evaluated, accurate evaluation is achieved, fine management of power enterprises is assisted, problems are found and processed in time, and safe and stable operation of a power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power system detection, and in particular to a full-process work quality and efficiency evaluation system for power consumption inspection based on big data. Background Art

[0002] In the power industry, power inspection is crucial to ensure the safe and stable operation of the power system. However, the existing quality and efficiency evaluation methods for power inspection have significant shortcomings.

[0003] On the one hand, data collection and integration are difficult. Multi-source data such as user inspection personnel information, equipment status data, and safety hazard records are scattered in different systems, with different formats and lack of effective integration. When the user inspection personnel's qualifications and training information are stored in the human resources and training systems, and the equipment data is in the equipment management system, these data are difficult to centrally obtain and analyze, and cannot provide a comprehensive basis for evaluation.

[0004] On the other hand, the evaluation index system and model are imperfect. Traditional evaluations rely more on manual experience or simple data statistics and lack a scientific index system. When evaluating, they often only focus on single indicators such as the number of tasks completed and the number of hidden dangers discovered, ignoring key factors such as operating specifications, process efficiency, and management impact. Moreover, the evaluation model cannot accurately reflect the complex relationship between various factors, and the weight determination is also relatively arbitrary. When determining the weight of the impact of personnel skills and hidden danger detection capabilities on the overall work quality and efficiency, there is a lack of scientific methods, resulting in inaccurate evaluation results and the inability to fully reflect the actual work situation, making it difficult to meet the needs of power companies for refined management and improved service quality. Summary of the invention

[0005] The purpose of the present invention is to overcome the above problems and provide a system for evaluating the quality and efficiency of the entire process of electricity inspection based on big data. To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] The whole process quality and efficiency evaluation system of electricity inspection based on big data includes data collection module, indicator system construction module, evaluation model construction module, evaluation analysis module and result output module;

[0007] The data acquisition module is used to collect multi-source data in the electricity inspection work;

[0008] The indicator system construction module is used to construct a quality and efficiency evaluation system for the entire process of electricity inspection;

[0009] The evaluation model building module is used to build a quality and efficiency evaluation model for the entire process of electricity inspection;

[0010] The evaluation and analysis module inputs the pre-processed data into the evaluation model for calculation and analysis to obtain the quality and efficiency evaluation results;

[0011] The result output module is used to display and output the evaluation results.

[0012] Furthermore, the multi-source data includes user and inspector information, inspection operation process records, equipment status data, safety hazard records, management documents and user and inspector operation data in virtual electricity inspection scenarios.

[0013] The data collection module includes a personnel information collection unit, an operation process recording unit, an equipment data collection unit, a hidden danger record collection unit, and a management data collection unit;

[0014] The personnel information collection unit obtains basic information, training record information and qualification certificate information of the inspection personnel by connecting with the enterprise human resources management system, training management system and qualification certification agency database, and stores it in the personnel information database with the personnel ID as the unique identifier;

[0015] The operation process recording unit uses sensors and data collectors installed on the inspection equipment to record the operation steps, operation time and operation location of the inspection personnel in real time, and stores them in the operation process database after data cleaning and preprocessing;

[0016] The equipment data collection unit is connected to the power equipment monitoring system and the equipment maintenance management system to collect equipment operation status data, models, specifications and maintenance records. For old equipment, manual entry is supported and the data is stored in the equipment information database after integration with the equipment ID as the unique identifier;

[0017] The hidden danger record collection unit allows the inspection personnel to record the type, location and severity of safety hazards through a dedicated mobile terminal APP. The APP automatically obtains the geographical location, and the collected data is stored in the hidden danger record database after review through text description and taking photos;

[0018] The management data collection unit collects management documents, rules and regulations, and work plan data from the enterprise document management system, and uses the inspectors to upload new data, which are stored in the management data database according to the file type and time classification.

[0019] Furthermore, the specific method of constructing the indicator system is as follows:

[0020] S11: Through questionnaire surveys, on-site interviews and expert consultations, we conducted in-depth research on actual electricity inspections and used principal component analysis and factor analysis to screen out the key element set A = {a1, a2, …, a n}, where a i represents the i-th key element, i = 1, 2, ..., n;

[0021] S12: Analyze the existing inspection operation process in detail, draw a flowchart and determine the key factor set B = {b1, b2, ..., b m}, evaluate the existing training system to determine the relevant factor set C = {c1, c2, ..., c k}, where b j Represents the jth factor in the operation process, j = 1, 2, ..., m, c l represents the lth factor in the training system, l = 1, 2, …, k;

[0022] S13: Through investigation and analysis, the analytic hierarchy process (AHP) is used to construct an evaluation index set D = {d1, d2, …, d p}, where d s represents the sth evaluation index, s = 1, 2, ..., p, and uses the AHP method to determine the weight w of each evaluation index s ,satisfy 0≤w s ≤1.

[0023] Furthermore, the specific method of constructing the evaluation model is as follows:

[0024] S21: Clean, normalize and extract features of the collected data, and divide it into training set and test set in a ratio of 7:3 or 8:2;

[0025] S22: Use entropy weight method and principal component analysis method to determine the weight of each evaluation indicator, and make appropriate adjustments according to the purpose and focus of the evaluation;

[0026] S23: Establish evaluation model function:

[0027] Where X = {x1, x2, …, x p} is the input data vector related to each evaluation index, x s is the evaluation index d s The corresponding input data, g s (x s ) is the evaluation index d s For input data x s The processing function is selected according to the nature of the evaluation index, the model is trained using the training set data, and the test set data is used to verify and optimize the model.

[0028] Furthermore, the specific evaluation method of the evaluation and analysis module is as follows:

[0029] S31: For the user inspection proficiency assessment, assume that the number of inspection tasks completed by the user inspection personnel in the virtual scene is n1, and the number of tasks completed correctly is n2, then the user inspection proficiency score is (When n1=0, S1=0);

[0030] S32: For the inspection process standard evaluation, let the number of steps specified in the inspection process be m1, and the number of steps correctly performed by the inspection personnel in the actual execution process be m2, then the inspection process standard score (When m1=0, S2=0);

[0031] S33: For the safety hazard detection capability assessment, let the number of actual safety hazards be k1, and the number of safety hazards discovered by the inspection personnel be k2. The safety hazard detection capability score is: (When k1=0, S3=0);

[0032] S34: Comprehensive score Among them, αi is the weight of each evaluation item, 0≤α i ≤1, where α i The AHP and entropy weight methods were used to determine the

[0033] Furthermore, the specific implementation method of the result output module is as follows:

[0034] S41: Comparison of different inspectors; screening out the inspector evaluation data to be compared from the evaluation result database, comparing the scores of each evaluation indicator, and calculating the score difference ΔS=S A -S B and score ratio And display the comparison results in the form of a bar chart or radar chart;

[0035] S42: Comparison of the same inspector in different time periods; extracting the evaluation data of the same inspector in different time periods from the evaluation result database, analyzing the changing trend of each evaluation indicator score over time, and calculating the score change rate The changing trend is displayed in the form of a line graph.

[0036] Furthermore, the evaluation model building module selects the processing function g s (x s ), for evaluation indicators with obvious linear relationships, linear regression functions are used for processing; for evaluation indicators with nonlinear relationships, neural network models are used for processing.

[0037] The advantages of the present invention are:

[0038] 1. The present invention provides a rich and accurate basis for evaluation by constructing a comprehensive data collection module, covering personnel information, operating procedures, equipment data, hidden danger records, management information and other data. On this basis, a scientific indicator system construction method and evaluation model are used to comprehensively consider factors such as personnel, specifications, equipment, hidden dangers and management, and accurately evaluate each link of electricity inspection work. Through quantitative evaluation of the work proficiency of inspection personnel, the degree of process standardization and the ability to discover hidden dangers, an objective comprehensive score is obtained, so that power companies can clearly understand the actual quality and efficiency of their work.

[0039] 2. The visualization result output provided by the present invention includes comparisons between different inspection personnel and the same inspection personnel in different time periods, so that the management of the power company can intuitively discover the differences between personnel and the development trends of individuals. Based on these evaluation results, the company can carry out targeted personnel training and management. For personnel with poor work performance, special training is arranged to improve their capabilities; for weak links in management, management strategies are adjusted in a timely manner. This helps to optimize resource allocation, improve work efficiency, and realize refined management of power companies.

[0040] 3. The present invention can timely discover problems and potential risks in electricity inspection work through accurate evaluation. By analyzing equipment data and hidden danger records, equipment failures and safety hazards can be discovered in advance, prompting enterprises to take timely measures to deal with them. At the same time, the evaluation of the operating specifications of inspection personnel can ensure that the inspection work is carried out strictly in accordance with standard procedures, reducing safety accidents caused by improper operation. By ensuring the high quality of electricity inspection work, the safe and stable operation of the power system is guaranteed, providing reliable power support for social and economic development. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The illustrative embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application.

[0042] In the attached picture:

[0043] Figure 1 This is an overall flow chart of the full-process work quality and efficiency evaluation system for electricity inspection based on big data in Example 1.

[0044] Figure 2 This is a flow chart of the data acquisition module of the full-process work quality and efficiency evaluation system for electricity inspection based on big data in Example 1.

[0045] Figure 3 This is a flowchart of the indicator system construction module of the full-process work quality and efficiency evaluation system for electricity inspection based on big data in Example 1.

[0046] Figure 4 This is a flow chart of the evaluation model construction module of the big data-based electricity inspection full-process work quality and efficiency evaluation system in Example 1.

[0047] Figure 5 This is a flow chart of the evaluation and analysis module of the full-process work quality and efficiency evaluation system for electricity inspection based on big data in Example 1.

[0048] Figure 6 This is a flow chart of the result output module of the full-process work quality and efficiency evaluation system for electricity inspection based on big data in Example 1. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0050] The present invention is described in detail and specifically by specific examples below to provide a better understanding of the present invention, but the following examples do not limit the protection scope of the present invention.

[0051] Example 1

[0052] The whole-process work quality and efficiency evaluation system of electricity consumption inspection based on big data includes data collection module, indicator system construction module, evaluation model construction module, evaluation analysis module and result output module.

[0053] The data acquisition module is used to collect multi-source data in electricity inspection work.

[0054] The technical effect of the data acquisition module is remarkable. It comprehensively collects multi-source data in electricity inspection work, providing a solid data foundation for subsequent evaluation work. By integrating the information of inspection personnel, inspection operation process records, equipment status data, safety hazard records, management documents and inspection personnel operation data in virtual electricity inspection scenarios, the integrity and comprehensiveness of the evaluation data are ensured. Data from different sources complement each other, allowing the evaluation to reflect the actual situation of electricity inspection work from multiple dimensions, avoiding evaluation deviations caused by missing data, and laying the foundation for accurately evaluating the quality and efficiency of electricity inspection work.

[0055] The indicator system construction module is used to construct a quality and efficiency evaluation system for the entire process of electricity inspection.

[0056] The indicator system construction module constructs a quality and efficiency evaluation system for the entire process of electricity inspection through scientific methods, ensuring the comprehensiveness and scientificity of the evaluation. Key elements are selected from actual surveys, relevant factors are determined by analyzing the operating procedures and training systems, and then the hierarchical analysis method is used to construct a set of evaluation indicators and determine the weights, so that the evaluation indicators can accurately reflect the key aspects of electricity inspection work, and the weight distribution of each indicator is reasonable, which can objectively measure the impact of different factors on work quality and efficiency.

[0057] The evaluation model building module is used to build a work quality and efficiency evaluation model for the entire electricity consumption inspection process.

[0058] The evaluation model building module preprocesses the collected data, uses a variety of methods to determine the indicator weights, establishes a suitable evaluation model function, and performs training and optimization. Data preprocessing improves data quality and provides a reliable data basis for model training; the combination of multiple weight determination methods makes the indicator weights more objective and reasonable; the selection of processing functions based on the nature of the indicators improves the adaptability and accuracy of the model. By training and optimizing the model, it is ensured that the model can accurately evaluate the quality and efficiency of electricity inspection work.

[0059] The evaluation and analysis module inputs the preprocessed data into the evaluation model for calculation and analysis to obtain quality and efficiency evaluation results.

[0060] The evaluation and analysis module inputs the pre-processed data into the evaluation model, evaluates the work quality and efficiency of the inspection personnel from multiple aspects and calculates the comprehensive score. The evaluation of work proficiency, process specifications and hidden danger detection ability can comprehensively and meticulously reflect the work performance of the inspection personnel. The calculation of the comprehensive score takes into account the weight of various aspects, more objectively measures the overall work quality and efficiency of the inspection personnel, and provides a strong basis for the performance appraisal and career development of the personnel.

[0061] The result output module is used to display and output the evaluation results.

[0062] The result output module displays the evaluation results in a visual way, including comparisons between different inspectors and the same inspector in different time periods. Visual display makes the evaluation results more intuitive and easy to understand, allowing managers to quickly understand the work performance and development trends of inspectors. Comparisons between different personnel help to discover the gaps between personnel and motivate employees to learn from and compete with each other; comparisons between the same person in different time periods can observe personal growth and progress, providing strong support for training and management decisions.

[0063] Furthermore, the multi-source data includes user and inspector information, inspection operation process records, equipment status data, safety hazard records, management documents and user and inspector operation data in virtual electricity inspection scenarios.

[0064] The data collection module includes a personnel information collection unit, an operation process recording unit, an equipment data collection unit, a hidden danger record collection unit, and a management data collection unit;

[0065] The personnel information collection unit obtains basic information, training record information and qualification certificate information of the inspection personnel by connecting with the enterprise human resource management system, training management system and qualification certification agency database, and stores it in the personnel information database with the personnel ID as the unique identifier.

[0066] The personnel information collection unit obtains comprehensive and accurate information about the power inspection personnel by connecting to multiple systems, and stores it with the personnel ID as the unique identifier. This method ensures the consistency and traceability of personnel information and avoids information confusion. Comprehensive personnel information helps to deeply evaluate the quality and efficiency of power inspection work from the perspective of personnel. For example, the professional ability of personnel can be evaluated based on training records and qualification certificate information, providing a basis for the reasonable deployment of personnel and targeted training, thereby improving overall work efficiency and quality.

[0067] The operation process recording unit utilizes sensors and data collectors installed on the inspection equipment to record the operation steps, operation time and operation location of the inspector in real time, and stores the data in the operation process database after data cleaning and preprocessing.

[0068] The operation process recording unit uses sensors and data collectors to record the operation information of the inspectors in real time, and stores it after cleaning and preprocessing. Real-time recording ensures the authenticity and timeliness of the operation information, and can accurately reflect the operation of the inspectors in actual work. By comparing with the standard operation process, irregular behaviors in the operation can be discovered in time, providing strong support for standardizing the operation process and improving the work quality. At the same time, the record of operation time and location also helps to analyze the work efficiency and the rationality of resource allocation.

[0069] The equipment data collection unit is connected to the power equipment monitoring system and the equipment maintenance management system to collect equipment operating status data, models, specifications and maintenance records. For old equipment, manual entry is supported and after integration, it is stored in the equipment information database with the equipment ID as the unique identifier.

[0070] The equipment data collection unit connects with relevant systems to collect equipment data, taking into account the manual entry of old equipment, and stores it with the equipment ID as the identifier. This method ensures the comprehensiveness and accuracy of equipment data, and can timely understand the operating status and historical maintenance of the equipment. When evaluating the quality and efficiency of power inspection work, equipment data can be used as an important reference to determine whether the inspection personnel have inspected the equipment in place and discover potential equipment problems, thereby ensuring the safe and stable operation of power equipment.

[0071] The hidden danger record collection unit allows inspection personnel to record the type, location and severity of safety hazards through a dedicated APP on a mobile terminal. The APP automatically obtains the geographic location, and collects data through text description and taking photos, and is stored in a hidden danger record database after review.

[0072] The hidden danger record collection unit uses a dedicated mobile terminal APP to facilitate users and inspectors to record safety hidden danger information, automatically obtain geographic location, and support text description and photo taking, which are stored after review. This method improves the convenience and accuracy of hidden danger records, and can record hidden dangers in a timely and detailed manner. The review mechanism ensures the reliability of the data, provides a real and effective basis for subsequent hidden danger processing and evaluation, and helps to eliminate safety hazards in a timely manner and ensure electricity safety.

[0073] The management data collection unit collects management documents, rules and regulations, and work plan data from the enterprise document management system, and uses the inspectors to upload new data, which are stored in the management data database according to the file type and time classification.

[0074] The management data collection unit collects data from the enterprise file management system and supports the inspection personnel to upload new data, which is stored by type and time. This allows the management data to be fully integrated and orderly managed, making it convenient to quickly query the required data during the evaluation process. Comprehensive management data provides rich information for the management level of the evaluation of power inspection work, which helps to find weak links in management, optimize management processes, and improve management efficiency.

[0075] Furthermore, the specific method of constructing the indicator system is as follows:

[0076] S11: Through questionnaire surveys, on-site interviews and expert consultations, we conducted in-depth research on actual electricity inspections and used principal component analysis and factor analysis to screen out the key element set A = {a1, a2, …, a n}, where a i represents the i-th key element, i = 1, 2, ..., n;

[0077] S12: Analyze the existing inspection operation process in detail, draw a flowchart and determine the key factor set B = {b1, b2, ..., b m}, evaluate the existing training system to determine the relevant factor set C = {c1, c2, ..., c k}, where b j Represents the jth factor in the operation process, j = 1, 2, ..., m, c l represents the lth factor in the training system, l = 1, 2, …, k;

[0078] S13: Through investigation and analysis, the analytic hierarchy process (AHP) is used to construct an evaluation index set D = {d1, d2, …, d p}, where ds represents the sth evaluation index, s = 1, 2, ..., p, and the AHP method is used to determine the weight w of each evaluation index s ,satisfy 0≤w s ≤1.

[0079] This method uses a variety of research methods and analysis methods to screen out key elements from a large number of actual situations, determine the key factors of the operating process and training system, and then construct a set of evaluation indicators covering multiple elements and determine reasonable weights. This comprehensive and scientific construction method enables the evaluation indicator system to closely fit the actual needs of electricity inspection work, accurately reflect all dimensions of work quality and efficiency, and provide a scientific and reasonable framework for subsequent evaluation work.

[0080] Furthermore, the specific method of constructing the evaluation model is as follows:

[0081] S21: Clean, normalize and extract features of the collected data, and divide it into training set and test set in a ratio of 7:3 or 8:2;

[0082] S22: Use entropy weight method and principal component analysis method to determine the weight of each evaluation indicator, and make appropriate adjustments according to the purpose and focus of the evaluation;

[0083] S23: Establish evaluation model function:

[0084] Where X = {x1, x2, …, x p} is the input data vector related to each evaluation index, x s is the evaluation index d s The corresponding input data, g s (x s ) is the evaluation index d s For input data x s The processing function is selected according to the nature of the evaluation index, the model is trained using the training set data, and the test set data is used to verify and optimize the model.

[0085] Furthermore, the evaluation model building module selects the processing function g s (x s ), for evaluation indicators with obvious linear relationships, linear regression functions are used for processing; for evaluation indicators with nonlinear relationships, neural network models are used for processing.

[0086] This method ensures the data quality and availability of the input model through a standardized data preprocessing process. The entropy weight method and principal component analysis method are combined to determine the weights, and they are adjusted according to the evaluation purpose to make the weights more in line with actual needs. According to the nature of the indicators, a suitable processing function is selected to build the model, and then the training set and test set are used for training and optimization, so that the evaluation model can accurately reflect the relationship between the quality and efficiency of electricity inspection work and each evaluation indicator, thereby improving the accuracy and reliability of the evaluation.

[0087] Furthermore, the specific evaluation method of the evaluation and analysis module is as follows:

[0088] S31: For the user inspection proficiency assessment, assume that the number of inspection tasks completed by the user inspection personnel in the virtual scene is n1, and the number of tasks completed correctly is n2, then the user inspection proficiency score is (When n1=0, S1=0);

[0089] S32: For the inspection process standard evaluation, let the number of steps specified in the inspection process be m1, and the number of steps correctly performed by the inspection personnel in the actual execution process be m2, then the inspection process standard score (When m1=0, S2=0);

[0090] S33: For the safety hazard detection capability assessment, let the number of actual safety hazards be k1, and the number of safety hazards discovered by the inspection personnel be k2. The safety hazard detection capability score is: (When k1=0, S3=0);

[0091] S34: Comprehensive score where α i is the weight of each evaluation item, 0≤α i ≤1, where α i The AHP and entropy weight methods were used to determine the

[0092] This evaluation method has established clear calculation rules for different evaluation aspects, and evaluates the work proficiency, process standardization and hidden danger detection ability of the inspection personnel through specific quantitative indicators, and then comprehensively evaluates the scores of various aspects to obtain a comprehensive evaluation result. This quantitative evaluation method makes the evaluation results more intuitive and accurate, and can clearly reflect the strengths and weaknesses of the inspection personnel in various aspects, providing a clear direction for targeted training and improvement.

[0093] Furthermore, the specific implementation method of the result output module is as follows:

[0094] S41: Comparison of different inspectors; screening out the inspector evaluation data to be compared from the evaluation result database, comparing the scores of each evaluation indicator, and calculating the score difference ΔS=SA -S B and score ratio And display the comparison results in the form of a bar chart or radar chart;

[0095] S42: Comparison of the same inspector in different time periods; extracting the evaluation data of the same inspector in different time periods from the evaluation result database, analyzing the changing trend of each evaluation indicator score over time, and calculating the score change rate The changing trend is displayed in the form of a line graph.

[0096] This implementation method screens and compares the evaluation data, calculates the score difference, score ratio and score change rate, and displays the results in the form of bar charts, radar charts and line charts. These visual charts can clearly present the relationship and change trend between the data, allowing managers to quickly grasp key information, make scientific and reasonable decisions, and improve management efficiency and decision accuracy.

[0097] The specific embodiments of the present invention are described in detail above, but they are only examples, and the present invention is not equivalent to the specific embodiments described above. For those skilled in the art, any equivalent modifications and substitutions made to the present invention are also within the scope of the present invention. Therefore, the equalization changes and modifications made without departing from the spirit and scope of the present invention should be included in the scope of the present invention.

Claims

1. The whole process quality and efficiency evaluation system of electricity inspection based on big data is characterized by: It includes data collection module, indicator system construction module, evaluation model construction module, evaluation analysis module and result output module; The data acquisition module is used to collect multi-source data in the electricity inspection work; The indicator system construction module is used to construct a quality and efficiency evaluation system for the entire process of electricity inspection; The evaluation model building module is used to build a quality and efficiency evaluation model for the entire process of electricity inspection; The evaluation and analysis module inputs the pre-processed data into the evaluation model for calculation and analysis to obtain the quality and efficiency evaluation results; The result output module is used to display and output the evaluation results.

2. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 1 is characterized by: The multi-source data includes user and inspector information, inspection operation process records, equipment status data, safety hazard records, management documents and user and inspector operation data in a virtual electricity inspection scenario.

3. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 2 is characterized by: The data collection module includes a personnel information collection unit, an operation process recording unit, an equipment data collection unit, a hidden danger record collection unit and a management data collection unit; The personnel information collection unit obtains basic information, training record information and qualification certificate information of the inspection personnel by connecting with the enterprise human resources management system, training management system and qualification certification agency database, and stores it in the personnel information database with the personnel ID as the unique identifier; The operation process recording unit uses sensors and data collectors installed on the inspection equipment to record the operation steps, operation time and operation location of the inspection personnel in real time, and stores them in the operation process database after data cleaning and preprocessing; The equipment data collection unit is connected to the power equipment monitoring system and the equipment maintenance management system to collect equipment operation status data, models, specifications and maintenance records. For old equipment, manual entry is supported and the data is stored in the equipment information database after integration with the equipment ID as the unique identifier; The hidden danger record collection unit allows the inspection personnel to record the type, location and severity of safety hazards through a dedicated mobile terminal APP. The APP automatically obtains the geographical location, and the collected data is stored in the hidden danger record database after review through text description and taking photos; The management data collection unit collects management documents, rules and regulations, and work plan data from the enterprise document management system, and uses the inspectors to upload new data, which are stored in the management data database according to the file type and time classification.

4. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 3 is characterized by: The specific methods for constructing the indicator system are as follows: S11: Through questionnaire surveys, on-site interviews and expert consultations, we conducted in-depth research on actual electricity inspections and used principal component analysis and factor analysis to screen out the key element set A = {a1, a2, …, a n }, where a i represents the i-th key element, i = 1, 2, ..., n; S12: Analyze the existing inspection operation process in detail, draw a flowchart and determine the key factor set B = {b1, b2, ..., b m }, evaluate the existing training system to determine the relevant factor set C = {c1, c2, ..., c k }, where b j Represents the jth factor in the operation process, j = 1, 2, ..., m, c l represents the lth factor in the training system, l = 1, 2, …, k; S13: Through investigation and analysis, the analytic hierarchy process (AHP) is used to construct an evaluation index set D = {d1, d2, …, d p }, where d s represents the sth evaluation index, s = 1, 2, ..., p, and uses the AHP method to determine the weight w of each evaluation index s ,satisfy 0≤w s ≤1.

5. The whole-process quality and efficiency evaluation system for electricity inspection based on big data according to claim 4 is characterized by: The specific method of building the evaluation model is as follows: S21: Clean, normalize and extract features of the collected data, and divide it into training set and test set in a ratio of 7:3 or 8:2; S22: Use entropy weight method and principal component analysis method to determine the weight of each evaluation indicator, and make appropriate adjustments according to the purpose and focus of the evaluation; S23: Establish evaluation model function: Where X = {x1, x2, …, x p } is the input data vector related to each evaluation index, x s is the evaluation index d s The corresponding input data, g s (x s ) is the evaluation index d s For input data x s The processing function is selected according to the nature of the evaluation index, the model is trained using the training set data, and the test set data is used to verify and optimize the model.

6. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 5 is characterized by: The specific evaluation method of the evaluation and analysis module is as follows: S31: For the user inspection proficiency assessment, assume that the number of inspection tasks completed by the user inspection personnel in the virtual scene is n1, and the number of tasks completed correctly is n2, then the user inspection proficiency score is: S32: For the inspection process standard evaluation, let the number of steps specified in the inspection process be m1, and the number of steps correctly performed by the inspection personnel in the actual execution process be m2, then the inspection process standard score (When m1=0, S2=0); S33: For the safety hazard detection capability assessment, let the number of actual safety hazards be k1, and the number of safety hazards discovered by the inspection personnel be k2. The safety hazard detection capability score is: S34: Comprehensive score where α i is the weight of each evaluation item, 0≤α i ≤1, where α i The AHP and entropy weight methods were used to determine the 7. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 6 is characterized by: The specific implementation method of the result output module is as follows: S41: Comparison of different inspectors; screening out the inspector evaluation data to be compared from the evaluation result database, comparing the scores of each evaluation indicator, and calculating the score difference ΔS=S A -S B and score ratio And display the comparison results in the form of a bar chart or radar chart; S42: Comparison of the same inspector in different time periods; extracting the evaluation data of the same inspector in different time periods from the evaluation result database, analyzing the changing trend of each evaluation indicator score over time, and calculating the score change rate The changing trend is displayed in the form of a line graph.

8. The whole-process electricity inspection work quality and efficiency evaluation system based on big data according to claim 7 is characterized by: The evaluation model building module selects the processing function g s (x s ), for evaluation indicators with obvious linear relationships, linear regression function is used for processing; For evaluation indicators with nonlinear relationships, neural network models are used for processing.

Images