Decision and management system based on operation and maintenance data

Abstract

The invention discloses a decision-making and management system based on operation and maintenance data, relates to the technical field of data processing, and solves the problem that a decision-making result is not accurate enough due to the fact that the matching condition and the advantages and disadvantages of personnel, vehicles and tools are not considered in the decision-making process. The system comprises a data acquisition and monitoring unit and an evaluation and management unit, the data acquisition and monitoring unit comprises a data storage module and a data updating module, the data storage module is used for storing personnel information required by power grid operation and maintenance operation, and the data updating module is used for updating stored data in the data storage module. The evaluation and management unit is used for calculating a personnel comprehensive score, a vehicle comprehensive score and a tool comprehensive score, finally, combining the matching coefficient, constructing a target function by taking the matching factor and the comprehensive evaluation factor maximization as a target, and solving the target function to obtain a comprehensive evaluation result; decision data support can be provided for operation and maintenance work arrangement personnel, vehicles and tools.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a decision-making and management system based on operation and maintenance data. Background Art

[0002] Digital management of power grid data is crucial for daily operation and maintenance tasks. Through the large-scale deployment of smart meters and sensors, it realizes real-time monitoring and data collection of the power grid operation status. The application of this technology not only improves the efficiency of power grid operation, but also significantly improves the level of intelligent operation and maintenance of the power grid through load forecasting and substation optimization site selection. Digital technology enables power grid data to be collected and stored efficiently, providing a solid foundation for data analysis and application. It optimizes the resource allocation of personnel, vehicles and tools, reduces emergency response time, and reduces power outages through accurate load forecasting and fault prediction, improving the continuity and stability of power supply.

[0003] However, the current resource allocation of personnel, vehicles and tools usually simply arranges idle personnel, vehicles and tools to respond, and hardly considers the matching of personnel, vehicles and tools and what kind of personnel, vehicles and tools to arrange to maximize the effect. In other words, the existing resource allocation process for personnel, vehicles and tools does not consider the matching situation and the quality of personnel, vehicles and tools in the decision-making process, which leads to inaccurate decision results.

[0004] In view of this, a decision-making and management system based on operation and maintenance data is needed. Summary of the invention

[0005] In view of the problem that the matching situation and the quality of personnel, vehicles and tools are not considered in the process of making decisions in the prior art, which leads to inaccurate decision results, the present invention provides a decision and management system based on operation and maintenance data, which can output comprehensive scores of personnel, vehicles and tools. With the support of various comprehensive scores, combined with matching coefficients, an objective function is constructed with the goal of maximizing matching factors and comprehensive evaluation factors. By solving the objective function, decision data support can be provided for arranging personnel, vehicles and tools for each operation and maintenance work. The specific technical scheme is as follows:

[0006] A decision-making and management system based on operation and maintenance data, comprising:

[0007] The data acquisition and monitoring unit includes a data storage module and a data update module. The data storage module is used to store personnel information required for power grid operation and maintenance, and the personnel information includes personnel qualification certificates, the number of positive evaluations obtained by the personnel, and the number of negative evaluations obtained by the personnel. The data update module updates the stored data in the data storage module according to the real-time collected data dynamics;

[0008] The evaluation and management unit includes a comprehensive evaluation module for calculating the comprehensive score of personnel. The specific calculation formula is as follows:

[0009]

[0010] In the formula, μ i is the weight coefficient of the i-th personnel qualification certificate, L i is the level of the i-th personnel qualification certificate, n is the total number of personnel qualification certificates, F 积极 The number of positive evaluations received by the personnel, F 消极 is the number of negative evaluations received by the personnel, F 重复警告_j is the number of repeated warnings of the jth warning type, m is the total number of warning types of repeated warnings, and λ1, λ2, λ3, and λ4 are the weight coefficients of their corresponding product terms.

[0011] Preferably, the evaluation and management unit further includes a vehicle comprehensive evaluation module, which is used to obtain a comprehensive vehicle score, and the specific calculation formula is as follows:

[0012]

[0013] Where, T year_1 is the age of the vehicle, F fault_1 is the total number of vehicle failures, as above, α1 and α2 are the weight coefficients of their corresponding product terms.

[0014] Preferably, the evaluation and management unit further includes a tool comprehensive evaluation module, which is used to obtain a tool comprehensive score. The specific calculation formula is as follows:

[0015]

[0016] Where, T year_2 is the tool life, F fault_2 is the total number of tool failures, as above, β1 and β2 are the weight coefficients of their corresponding product terms.

[0017] Preferably, a decision-making auxiliary unit is also included, and the decision-making auxiliary unit outputs a decision by constructing and solving an objective function, and the objective function is specifically as follows:

[0018] max Z=δ2P人_综合 +δ3P 车_综合 +δ4P 物_综合

[0019] Where δ2, δ3, and δ4 are the weight coefficients of the comprehensive score of personnel, the comprehensive score of vehicles, and the comprehensive score of tools.

[0020] Preferably, a decision-making auxiliary unit is also included, and the decision-making auxiliary unit outputs a decision by constructing and solving an objective function, and the objective function is specifically as follows:

[0021] max Z=δ1P matching +δ2P 人_综合 +δ3P 车_综合 +δ4P 物_综合

[0022] Where δ1, δ2, δ3, and δ4 are the weight coefficients of personnel matching coefficient, personnel comprehensive score, vehicle comprehensive score, and tool comprehensive score, P matching is the personnel matching coefficient, and the calculation formula is as follows:

[0023] P matching =k1P licence +k2P professional

[0024] P licence is the license matching coefficient. When the operator in charge of the operation and maintenance process has the license required by the current operation and maintenance task, the coefficient is 1, otherwise it is 0. professional is the job title matching coefficient. When the personnel used for operation and maintenance have the job title required by the current operation and maintenance task, the coefficient is 1. k1 and k2 are the weights of the license matching coefficient and the job title matching coefficient respectively.

[0025] Preferably, there are also constraints, including:

[0026] Staff availability constraints:

[0027] R 人 ≠0

[0028] In the formula, R 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle;

[0029] Constraints on comprehensive staff scores:

[0030] P 人_综合 ≥P 人_综合_min

[0031] Where P 人_综合_min It is the minimum comprehensive score constraint for personnel, that is, this value is the minimum value of the comprehensive score of personnel that can be tolerated.

[0032] Vehicle Idle Condition Constraints:

[0033] R 车 ≠0

[0034] In the formula, R 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle;

[0035] Vehicle comprehensive score constraints:

[0036] P 车_综合 ≥P 车_综合_min

[0037] Where P 人_综合_min is the minimum vehicle comprehensive score constraint, that is, this value is the minimum value of the vehicle comprehensive score that can be tolerated.

[0038] Tool Idle Condition Constraints:

[0039] R 物 ≠0

[0040] In the formula, R 物 is the tool idle condition coefficient, which is 1 when the tool is idle and 0 when the tool is not idle;

[0041] Tool comprehensive score constraints:

[0042] P 物_综合 ≥P 物_综合_min

[0043] Where P 物_综合_min is the minimum vehicle comprehensive score constraint, that is, this value is the minimum value of the vehicle comprehensive score that can be tolerated.

[0044] Preferably, the data collection and monitoring unit further includes a data verification module, which is used to verify whether the name of the person corresponds to the name on the person's qualification certificate, license, or professional title certificate. The specific operation is as follows:

[0045] S1: Obtain images (scans or pictures) of personnel qualification certificates, licenses, and professional title certificates, and perform enhancement processing on the acquired images, including denoising, contrast enhancement, and sharpening, to improve the recognizability of the text;

[0046] S2: Use Tesseract from the open source OCR library to convert the text in the image into a machine-readable text format;

[0047] S3: Identify and extract the name based on the trained model, and then match the identified name with the person's name in the input storage module to verify the accuracy of the certificate name.

[0048] S4: If there is no match, an alarm signal is issued.

[0049] Preferably, the data verification module is also used to verify whether the personnel photo corresponds to the photo on the personnel qualification certificate, license, or professional title certificate. The specific steps are as follows:

[0050] S01: Data collection: Collect photos of personnel qualification certificates, licenses, professional title certificates and photos of personnel to be verified, and use OpenCV's face detection function to locate the face area in the images of qualification certificates, licenses, and professional title certificates. Based on the detected face area, crop the face image from the original image and save it;

[0051] S02: Image preprocessing: Use OpenCV to normalize the photos, including resizing and graying them;

[0052] S03: Feature extraction: Use the deep learning model CNN to extract facial feature vectors;

[0053] S04: Model training: Based on the convolutional neural network (CNN) model, training is performed using the collected data set;

[0054] S05: Feature comparison: compare the feature vector of the photo of the person to be verified with the feature vector of the photo on the qualification certificate, license, or professional title certificate, and use cosine similarity to calculate the similarity between the two;

[0055] S06: Threshold setting: Set a similarity threshold. If the comparison result exceeds this threshold, the two photos are considered to be of the same person; otherwise, they are considered to be different people.

[0056] S07: Result output: If the faces on the personnel qualification certificate, license, professional title certificate and personnel photo are the same person when compared, the result of verification passing is output; otherwise, the result of verification failure is output and an alarm signal is sent.

[0057] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the decision-making and management system based on operation and maintenance data as described above.

[0058] A processor is used to run a program, wherein the program executes the decision-making and management system based on operation and maintenance data as described above when running.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. The present invention includes a data acquisition and monitoring unit and an evaluation and management unit, wherein the data acquisition and monitoring unit includes a data storage module and a data update module, wherein the data storage module is used to store personnel information required for power grid operation and maintenance, and the personnel information includes personnel qualification certificates, the number of positive evaluations obtained by the personnel, and the number of negative evaluations obtained by the personnel, and the data update module updates the stored data in the data storage module according to the real-time data collected. The evaluation and management unit includes a personnel comprehensive evaluation module for calculating the comprehensive score of the personnel. In the process of calculating the comprehensive score of the personnel, the four dimensions of qualification certificates, positive feedback, negative feedback, and repeated warning times are comprehensively considered, so that the comprehensive score of the personnel is sufficient to evaluate the pros and cons of a person, and further facilitates the provision of data support for decision-making, so that managers can refer to data when allocating resources.

[0061] 2. The present invention also calculates the comprehensive vehicle score and the comprehensive tool score. With the support of each comprehensive score and in combination with the matching coefficient, an objective function is constructed with the goal of maximizing the matching factor and the comprehensive evaluation factor. By solving the objective function, decision-making data support can be provided for arranging personnel, vehicles and tools for each operation and maintenance work. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0063] Figure 1 It is a schematic diagram of the overall framework of the system of the present invention;

[0064] Figure 2 A flowchart for verifying a name by the data verification module of the present invention;

[0065] Figure 3 This is a flow chart of model training of the present invention;

[0066] Figure 4 A flow chart of the data verification module of the present invention for verifying a face;

[0067] Figure 5 Schematic diagram of the specific steps of the gradient ascent method. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0070] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0071] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0072] In one embodiment of the present invention, a decision-making and management system based on operation and maintenance data is provided, such as Figure 1 As shown, including:

[0073] 1. Data acquisition and monitoring unit

[0074] The data acquisition and monitoring unit includes a data storage module, a data verification module and a data update module. The data storage module is used to store the personnel, vehicle and item information required for the power grid operation and maintenance operation. The data verification module is used to verify the accuracy of some important data or error-prone data in the data storage module. The data update module updates the stored data in the data storage module according to the verification result of the data verification module and the data dynamics collected in real time. The data storage module, the data verification module and the data update module are further described in detail below.

[0075] First, the data storage module is described. The data storage module stores personnel information, vehicle information and item information. The personnel information includes personnel identity information, personnel qualification information, personnel positive evaluation information, personnel negative evaluation information and personnel status;

[0076] Personnel identity information includes: name, photo, ID number, work number, etc.

[0077] Personnel qualification information includes: qualification certificates, licenses, professional titles and other personnel qualification certificates; among which, qualification certificates are stored in the form of scanned copies or photos.

[0078] Personnel positive evaluation information includes: the number of unit commendations, the number of positive feedback from users, etc.;

[0079] Personnel negative evaluation information includes: the number of unconventional operations, the number of warnings of the same type, etc. The unconventional operations include leaving the post and mistakenly entering the live interval;

[0080] Personnel status includes: idle status and non-idle status.

[0081] The vehicle information includes vehicle information, vehicle age, vehicle fault record and vehicle status; the vehicle information includes vehicle number and vehicle type, the vehicle fault record includes vehicle fault type and fault frequency, and the vehicle status includes idle state and non-idle state;

[0082] The tool information includes tool information, tool service life, tool failure record and tool status; the tool information includes tool type and tool number, the tool failure record includes tool failure type and the number of failures of the corresponding type, and the tool status includes idle state and non-idle state.

[0083] The data verification module is used to verify the information stored in the data storage module to ensure its authenticity. In this embodiment, the data verification module is used to verify the correspondence between the personnel identity information and the qualification information. This includes two information checks: one is that the personnel name corresponds to the name on the personnel qualification certificate, license, or professional title certificate; the other is that the personnel photo corresponds to the photo on the personnel qualification certificate, license, or professional title certificate. This ensures that "person and certificate correspond".

[0084] (I) The specific steps for verifying whether the name of a person corresponds to the name on the person's qualification certificate, license, or professional title certificate are as follows:

[0085] like Figure 2 As shown,

[0086] S1: Obtain images (scans or pictures) of personnel qualification certificates, licenses, and professional title certificates, and perform enhancement processing on the acquired images, including denoising, contrast enhancement, and sharpening, to improve the recognizability of the text;

[0087] S2: Use Tesseract from the open source OCR library to convert the text in the image into a machine-readable text format;

[0088] S3: Identify and extract the name based on the trained model, and then match the identified name with the person identity information (name) in the input storage module to verify the accuracy of the certificate name.

[0089] S4: If there is no match, an alarm signal is issued.

[0090] This step involves the training of the model, such as Figure 3 As shown, the training process is as follows:

[0091] 1. Data collection: Collect a large amount of labeled data, which contains the text on the qualification certificate and the corresponding person’s name. This data will be used to train and validate the model.

[0092] 2. Data preprocessing: Preprocess the collected data, including text cleaning (removing irrelevant characters, standardization), word segmentation and other steps to prepare data for model training.

[0093] 3. Data annotation: Use named entity recognition (NER) tools or manually to annotate name entities in the text. The annotated data format is usually IOB format, where I indicates inside the entity, B indicates the beginning of the entity, and O indicates non-entity.

[0094] 4. Model selection and training: BERT-based models are trained using preprocessed and annotated data.

[0095] (II) The specific steps for verifying whether the person's photo corresponds to the photo on the person's qualification certificate, license, or professional title certificate are as follows:

[0096] like Figure 4 As shown,

[0097] S01: Data collection: Collect photos of personnel qualification certificates, licenses, professional title certificates and photos of personnel to be verified, and use OpenCV's face detection function to locate the face area in the images of qualification certificates, licenses, and professional title certificates. Based on the detected face area, crop the face image from the original image and save it;

[0098] S02: Image preprocessing: Use image processing techniques, such as OpenCV, to normalize photos, including adjusting image size, grayscale, etc., to reduce variables in subsequent processing.

[0099] S03: Feature extraction: extract features from the detected face area. This embodiment uses a deep learning model CNN to extract face feature vectors.

[0100] S04: Model training: Build a convolutional neural network (CNN) model and train it with the collected dataset.

[0101] S05: Feature comparison: Compare the feature vector of the photo of the person to be verified with the feature vector of the photo on the qualification certificate, license, or professional title certificate. Calculate the similarity or distance between the two, such as using Euclidean distance or cosine similarity.

[0102] S06: Threshold setting: Set a similarity threshold according to business needs. If the comparison result exceeds this threshold, the two photos are considered to be of the same person; otherwise, they are considered to be different people.

[0103] S07: Result output: Output the verification conclusion according to the comparison result. If the faces on the personnel qualification certificate, license, professional title certificate and personnel photo are the same person when compared, the result of verification passing is output; otherwise, the result of verification failure is output and an alarm signal is sent.

[0104] The data update module is used to update the data in the data storage module. It is mainly updated in two ways. One is to arrange management personnel to check personnel information based on alarm signals and then change personnel information. The second is to update the corresponding storage information in the data storage module based on real-time power grid operation and maintenance status, such as fault type, fault time, user feedback and other data. The data update module is used to ensure the accuracy and timeliness of the data stored in the data storage module.

[0105] 2. Evaluation and Management Unit

[0106] The evaluation and management unit includes a personnel comprehensive evaluation module, a vehicle comprehensive evaluation module and an item comprehensive evaluation module. Among them, the personnel comprehensive evaluation module is used to output the personnel comprehensive score, the vehicle comprehensive evaluation module is used to output the vehicle comprehensive score, and the item comprehensive evaluation module is used to output the item comprehensive score. The personnel comprehensive score, vehicle comprehensive score and item comprehensive score are used to influence the decision generation of the subsequent decision unit.

[0107] The formula for calculating the comprehensive score of personnel is as follows:

[0108]

[0109] In the formula, μ i is the weight coefficient of the i-th personnel qualification certificate, L i is the level of the i-th personnel qualification certificate. In practical applications, different L can be set according to different levels. i The higher the level, the i The higher the level, the higher the value. For example, the values ​​1, 2, and 3 in level 1, 2, and 3 can be directly used as L. i Value, as long as the level is higher, L i The higher the requirement, the better. The specific value is set by the actual application needs. n is the total number of personnel qualification certificates, F积极 The number of positive evaluations received by the personnel, F 消极 is the number of negative evaluations received by the person, F 重复警告_j is the number of repeated warnings of the jth warning type, m is the total number of warning types of repeated warnings, λ1, λ2, λ3, λ4 are the weight coefficients of their corresponding product terms, which are used to reflect the different degrees of influence of qualification certificates, positive feedback, negative feedback, and the number of repeated warnings on the comprehensive score of personnel.

[0110] The formula for calculating the vehicle's comprehensive score is as follows:

[0111]

[0112] Where, T year_1 is the age of the vehicle, F fault_1 is the total number of vehicle failures. As above, α1 and α2 are the weight coefficients of the corresponding product terms, which are used to reflect the different degrees of influence of vehicle service life and vehicle failure times on the comprehensive score of personnel.

[0113] The formula for calculating the comprehensive score of the tool is as follows:

[0114]

[0115] Where, T year_2 is the tool life, F fault_2 is the total number of tool failures. Same as above, β1 and β2 are the weight coefficients of the corresponding product terms, which are used to reflect the different degrees of influence of tool service life and the total number of tool failures on the comprehensive score of personnel.

[0116] 3. Decision Support Unit

[0117] The decision support unit provides decision data support for arranging personnel, vehicles and tools for each operation and maintenance work by constructing an objective function.

[0118] The objective function is constructed with the goal of maximizing the matching factor and the comprehensive evaluation factor, as follows:

[0119] max Z=δ1P matching +δ2P 人_综合 +δ3P 车_综合 +δ4P 物_综合

[0120] Where δ1, δ2, δ3, and δ4 are the weight coefficients of personnel matching coefficient, personnel comprehensive score, vehicle comprehensive score, and tool comprehensive score, P matching is the personnel matching coefficient, and the calculation formula is as follows:

[0121] P matching =k1P licence +k2Pprofessional

[0122] P licence is the license matching coefficient. When the operator in charge of the operation and maintenance process has the license required by the current operation and maintenance task, the coefficient is 1, otherwise it is 0. professional is the job title matching coefficient. When the personnel used for operation and maintenance have the job title required by the current operation and maintenance task, the coefficient is 1, otherwise it is 0. k1 and k2 are the weights of the license matching coefficient and the job title matching coefficient, respectively, reflecting the different levels of importance attached to licenses and job titles. The more importance is attached, the higher the corresponding weight is.

[0123] Set constraints, which include:

[0124] Staff availability constraints:

[0125] R 人 ≠0

[0126] In the formula, R 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle;

[0127] Constraints on comprehensive staff scores:

[0128] P 人_综合 ≥P 人_综合_min

[0129] Where P 人_综合_min It is the minimum comprehensive score constraint for personnel, that is, this value is the minimum value of the comprehensive score of personnel that can be tolerated.

[0130] Vehicle Idle Condition Constraints:

[0131] R 车 ≠0

[0132] In the formula, R 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle;

[0133] Vehicle comprehensive score constraints:

[0134] P 车_综合 ≥P 车_综合_min

[0135] Where P 人_综合_min is the minimum vehicle comprehensive score constraint, that is, this value is the minimum value of the vehicle comprehensive score that can be tolerated.

[0136] Tool Idle Condition Constraints:

[0137] R 物 ≠0

[0138] In the formula, R 物 is the tool idle condition coefficient, which is 1 when the tool is idle and 0 when the tool is not idle;

[0139] Tool comprehensive score constraints:

[0140] P 物_综合 ≥P 物_综合_min

[0141] Where P 物_综合_min is the minimum vehicle comprehensive score constraint, that is, this value is the minimum value of the vehicle comprehensive score that can be tolerated.

[0142] Solve the objective function and obtain the best operation and maintenance work arrangement, including personnel arrangement, vehicle arrangement and tool arrangement.

[0143] This embodiment uses the gradient ascent algorithm. The gradient ascent method is an iterative method that gradually adjusts parameters along the direction of the objective function gradient to find the maximum value of the function. Figure 5 As shown, the following are the specific steps of the gradient ascent method:

[0144] Step 1: Get the data set for decision making and randomly select an initial point as the starting point;

[0145] Step 2: Calculate the gradient of the objective function Z at the current point;

[0146] Step 3: Update the parameters along the direction of the gradient, define the learning rate, and control the step size;

[0147] Step 4: Check whether the magnitude of the gradient is less than a preset threshold, or check whether the value of the objective function changes very little in several consecutive iterations. If so, the algorithm is considered to have converged.

[0148] Step 5: If there is no convergence, return to step 2 and continue iterating;

[0149] Step 6: When the algorithm converges, output the value of the current decision.

[0150] In summary, the present invention includes a data acquisition and monitoring unit and an evaluation and management unit, wherein the data acquisition and monitoring unit includes a data storage module and a data update module, wherein the data storage module is used to store the personnel information required for the power grid operation and maintenance operation, the personnel information includes personnel qualification certificates, the number of positive evaluations obtained by the personnel, and the number of negative evaluations obtained by the personnel, and the data update module updates the stored data in the data storage module according to the real-time data collected. The evaluation and management unit includes a personnel comprehensive evaluation module for calculating the comprehensive score of the personnel. In the process of calculating the comprehensive score of the personnel, the four dimensions of qualification certificates, positive feedback, negative feedback, and repeated warning times are comprehensively considered, so that the comprehensive score of the personnel is sufficient to evaluate the pros and cons of a person, and further facilitates the provision of data support for decision-making, so that managers can refer to data when allocating resources. The present invention also calculates the comprehensive score of the vehicle and the comprehensive score of the tool. With the support of each comprehensive score, combined with the matching coefficient, the objective function is constructed with the goal of maximizing the matching factor and the comprehensive evaluation factor. By solving the objective function, it can provide decision-making data support for the arrangement of personnel, vehicles and tools for each operation and maintenance work.

[0151] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0152] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A decision-making and management system based on operation and maintenance data, characterized in that: include: The data acquisition and monitoring unit includes a data storage module and a data update module. The data storage module is used to store personnel information required for power grid operation and maintenance, and the personnel information includes personnel qualification certificates, the number of positive evaluations obtained by the personnel, and the number of negative evaluations obtained by the personnel. The data update module updates the stored data in the data storage module according to the real-time collected data dynamics; The evaluation and management unit includes a comprehensive evaluation module for calculating the comprehensive score of personnel. The specific calculation formula is as follows: In the formula, μ i is the weight coefficient of the i-th personnel qualification certificate, L i is the level of the i-th personnel qualification certificate, n is the total number of personnel qualification certificates, F 积极 The number of positive evaluations received by the personnel, F 消极 is the number of negative evaluations received by the personnel, F 重复警告_j is the number of repeated warnings of the jth warning type, m is the total number of warning types of repeated warnings, and λ1, λ2, λ3, and λ4 are the weight coefficients of their corresponding product terms.

2. A decision-making and management system based on operation and maintenance data according to claim 1, characterized in that: The evaluation and management unit also includes a vehicle comprehensive evaluation module, which is used to obtain a comprehensive vehicle score. The specific calculation formula is as follows: Where, T year_1 is the age of the vehicle, F fault_1 is the total number of vehicle failures, as above, α1 and α2 are the weight coefficients of their corresponding product terms.

3. A decision-making and management system based on operation and maintenance data according to claim 2, characterized in that: The evaluation and management unit also includes a tool comprehensive evaluation module, which is used to obtain a comprehensive tool score. The specific calculation formula is as follows: Where, T year_2 is the tool life, F fault_2 is the total number of tool failures, as above, β1 and β2 are the weight coefficients of their corresponding product terms.

4. A decision-making and management system based on operation and maintenance data according to claim 3, characterized in that: It also includes a decision support unit, which outputs a decision by constructing and solving an objective function. The objective function is as follows: max Z=δ2P 人_综合 +δ3P 车_综合 +δ4P 物_综合 Where δ2, δ3, and δ4 are the weight coefficients of the comprehensive score of personnel, the comprehensive score of vehicles, and the comprehensive score of tools.

5. A decision-making and management system based on operation and maintenance data according to claim 3, characterized in that: It also includes a decision support unit, which outputs a decision by constructing and solving an objective function. The objective function is as follows: max Z=δ1P matching +δ2P 人_综合 +δ3P 车_综合 +δ4P 物_综合 Where δ1, δ2, δ3, and δ4 are the weight coefficients of personnel matching coefficient, personnel comprehensive score, vehicle comprehensive score, and tool comprehensive score, P matching is the personnel matching coefficient, and the calculation formula is as follows: P matching =k1P licence +k2P professional P licence is the license matching coefficient. When the operator in charge of the operation and maintenance process has the license required by the current operation and maintenance task, the license matching coefficient is 1, otherwise it is 0. professional is the job title matching coefficient. When the personnel used in the operation and maintenance process have the job title required by the current operation and maintenance task, the job title matching coefficient is 1, otherwise it is 0. k1 and k2 are the weights of the license matching coefficient and the job title matching coefficient respectively.

6. A decision-making and management system based on operation and maintenance data according to any one of claims 4-5, characterized in that: There are also constraints, including: Staff availability constraints: R 人 ≠0 In the formula, R 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle; Constraints on comprehensive staff scores: P 人_综合 ≥P 人_综合_min Where P 人_综合_min The minimum comprehensive score constraint for personnel; Vehicle Idle Condition Constraints: R 车 ≠0 In the formula, R 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle; Vehicle comprehensive score constraints: P 车_综合 ≥P 车_综合_min Where P 人_综合_min is the minimum vehicle comprehensive score constraint; Tool Idle Condition Constraints: R 物 ≠0 In the formula, R 物 is the tool idle condition coefficient, which is 1 when the tool is idle and 0 when the tool is not idle; Tool comprehensive score constraints: P 物_综合 ≥P 物_综合_min Where P 物_综合_min is the minimum vehicle comprehensive score constraint.

7. A decision-making and management system based on operation and maintenance data according to any one of claims 1 to 5, characterized in that: The data collection and monitoring unit also includes a data verification module, which is used to verify whether the name of the person corresponds to the name on the person's qualification certificate, license, or professional title certificate. The specific operation is as follows: S1: Obtain images of personnel qualification certificates, licenses, and professional title certificates, and perform enhancement processing on the acquired images, including denoising, contrast enhancement, and sharpening, to improve the recognizability of the text; S2: Use Tesseract from the open source OCR library to convert the text in the image into a machine-readable text format; S3: Recognize and extract the name based on the trained model, and then match the recognized name with the person's name in the input storage module to verify the accuracy of the certificate name; S4: If there is no match, an alarm signal is issued.

8. A decision-making and management system based on operation and maintenance data according to claim 7, characterized in that: The data verification module is also used to verify whether the person's photo corresponds to the photo on the person's qualification certificate, license, or professional title certificate. The specific steps are as follows: S01: Data collection: Collect photos of personnel qualification certificates, licenses, professional title certificates and photos of personnel to be verified, and use OpenCV's face detection function to locate the face area in the images of qualification certificates, licenses, and professional title certificates. Based on the detected face area, crop the face image from the original image and save it; S02: Image preprocessing: Use OpenCV to normalize the photos, including resizing and graying them; S03: Feature extraction: Use the deep learning model CNN to extract facial feature vectors; S04: Model training: Based on the convolutional neural network (CNN) model, training is performed using the collected data set; S05: Feature comparison: compare the feature vector of the photo of the person to be verified with the feature vector of the photo on the qualification certificate, license, or professional title certificate, and use cosine similarity to calculate the similarity between the two; S06: Threshold setting: Set a similarity threshold. If the comparison result exceeds this threshold, the two photos are considered to be of the same person; otherwise, they are considered to be different people. S07: Result output: If the faces on the personnel qualification certificate, license, professional title certificate and personnel photo are the same person when compared, the result of verification passing is output; otherwise, the result of verification failure is output and an alarm signal is sent.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the decision-making and management system based on operation and maintenance data according to any one of claims 1 to 6.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the decision-making and management system based on operation and maintenance data as described in any one of claims 1 to 6.

Images