Search

CN-121998660-A - Power industry software provider assessment system based on principal component analysis

CN121998660ACN 121998660 ACN121998660 ACN 121998660ACN-121998660-A

Abstract

The invention belongs to the technical field of software provider assessment, and discloses a power industry software provider assessment system based on principal component analysis, which comprises a data acquisition module, an index definition module, a principal component analysis module, an assessment calculation module and a visual display module, wherein the data acquisition module is used for acquiring a power supply of a power supply; the power industry software provider assessment system based on principal component analysis can automatically process assessment data and output visual analysis results of comprehensive capacity of providers. By comparing the vendor ranking generated by the system with the manual assessment results, the accuracy and rationality of the model is assessed. If the correlation between the model result and the manual evaluation result is obvious, the validity of the model is verified, and if the model result is inconsistent, the index selection, weight distribution or principal component extraction method can be optimized. In addition, in the verification process, the robustness of the transverse model can be tested by a leave-one-out verification or cross-verification method, so that the applicability and popularization of the transverse model on different data sets are ensured.

Inventors

  • LONG FEI
  • WEI XIAOYAN
  • ZHAO QINGYAO
  • Mei ziwei
  • HU JUNGUO
  • CHEN CHEN
  • WANG XIAORUI
  • LI YING
  • ZHENG LEI
  • Hou dai
  • ZHUANG YAN
  • LIU XIN
  • HUANG JUNDONG
  • ZHAN WEI
  • YU MINGYANG
  • JIN BO
  • YU ZHENG
  • ZHA ZHIYONG
  • GAO FEI
  • CHEN JIALIN
  • XU HUAN
  • XIA FAN

Assignees

  • 国网湖北省电力有限公司信息通信公司

Dates

Publication Date
20260508
Application Date
20251231

Claims (10)

  1. 1. A power industry software provider assessment system based on principal component analysis, comprising: The system comprises a data acquisition module, an index definition module, a principal component analysis module, an evaluation calculation module and a visual display module; the data acquisition module is connected with the index definition module and the visual display module and is used for acquiring provider related data from historical provider evaluation records, purchase contracts and project delivery data sources of the power industry; The index definition module is connected with the data acquisition module, the evaluation calculation module and the visual display module and is used for containing 12 evaluation indexes of technical reserve, enterprise qualification, quality promise, financial strength and software applicability; the principal component analysis module is connected with the index definition module and the evaluation calculation module and is used for carrying out standardized processing on index data, reducing the dimension by using a principal component analysis method and extracting a few key principal components to represent the comprehensive capacity of a provider; the evaluation calculation module is connected with the index definition module, the principal component analysis module and the visual display module and is used for calculating the comprehensive score of the provider based on the principal component score; The visual display module is connected with the data acquisition module, the index definition module and the evaluation calculation module and used for displaying evaluation results and comparative analysis of all suppliers in the forms of radar graphs and bar graphs.
  2. 2. The power industry software provider evaluation system based on principal component analysis of claim 1, wherein the data acquisition module: 1) And (3) data acquisition: importing provider data from a purchasing system or Excel file into a database using a database API or ETL tool; The data field comprises 12 indexes of technical reserve, enterprise qualification and quality commitment and basic information of suppliers; 2) Data cleaning: Processing the missing value in the data, namely filling, interpolating or deleting the missing record through the mean value to ensure the data integrity; Checking abnormal values of data, and identifying and processing the abnormal values through a box diagram or Z score method; 3) Data normalization: Normalizing each index according to the following formula: wherein X is an original value, mu is a mean value, sigma is a standard deviation, and X' is a standardized value.
  3. 3. The power industry software provider evaluation system based on principal component analysis of claim 1, wherein the principal component analysis module: 1) Constructing a covariance matrix: Calculating covariance matrix of each index by using the normalized data: 2) Calculating eigenvalues and eigenvectors: Calculating eigenvalues and eigenvectors using linear algebraic methods or numpy.1ina1g.eig functions that call Python; 3) The main components are selected: according to the accumulated contribution rate ) Selecting a main component to enable the accumulated contribution rate to reach more than 85%; 4) Calculating the principal component score: Calculating principal component scores according to the selected feature vectors and the original data: Wherein X is standardized data, and Vj is a feature vector of a j-th principal component.
  4. 4. The power industry software provider evaluation system based on principal component analysis of claim 1, wherein the evaluation module: 1) And (3) comprehensive score calculation: The comprehensive score formula is: Wherein, the The score is a score of the principal component, The ratio of the characteristic value to the total characteristic value; 2) Ranking of suppliers; 3) An assessment report is generated.
  5. 5. The power industry software provider assessment system based on principal component analysis of claim 4, wherein the provider ranks: The composite scores of all suppliers are arranged in descending order to generate a ranked list of suppliers.
  6. 6. The power industry software provider evaluation system based on principal component analysis of claim 4, wherein the generating an evaluation report: and summarizing the evaluation results, including the comprehensive scores, the ranks and the index scores of all suppliers, and exporting the evaluation results into PDF or Excel files.
  7. 7. A power industry software provider assessment method based on principal component analysis embodying the power industry software provider assessment system based on principal component analysis as claimed in any one of claims 1 to 6, characterized in that the power industry software provider assessment method based on principal component analysis comprises: step 1, acquiring relevant data of suppliers from historical supplier evaluation records, purchase contracts and project delivery data sources of the power industry through a data acquisition module; Step 2, 12 evaluation indexes including technical reserve, enterprise qualification, quality promise, financial strength and software applicability are contained through an index definition module; Step 3, carrying out standardized processing on the index data through a principal component analysis module, reducing the dimension by using a principal component analysis method, and extracting a few key principal components to represent the comprehensive capacity of a provider; step 4, calculating the comprehensive score of the provider based on the principal component score through an evaluation calculation module; And 5, displaying the evaluation result and the comparison analysis of each provider by using a radar chart and a bar chart form through a visual display module.
  8. 8. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the power industry software provider assessment method based on principal component analysis of claim 7.
  9. 9. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the power industry software provider assessment method based on principal component analysis as claimed in claim 7.
  10. 10. An information data processing terminal for implementing the power industry software provider assessment system based on principal component analysis according to any one of claims 1 to 6.

Description

Power industry software provider assessment system based on principal component analysis Technical Field The invention belongs to the technical field of software provider assessment, and particularly relates to a power industry software provider assessment system based on principal component analysis. Background Power industry software providers are primarily those companies that focus on providing informative solutions and software services for the power industry. These suppliers typically provide software that encompasses aspects of planning, management, monitoring, and operation of power engineering projects, with the aim of improving the operational efficiency and management level of power enterprises. However, existing assessment of the power industry software suppliers is manually assessed, and cannot automatically process assessment data and output visual analysis results of the comprehensive capabilities of the suppliers. Through the above analysis, the problems and defects existing in the prior art are as follows: The existing evaluation of the power industry software suppliers can not automatically process evaluation data and output visual analysis results of comprehensive capacities of the suppliers through manual evaluation. Disclosure of Invention Aiming at the problems existing in the prior art, the invention provides a power industry software provider assessment system based on principal component analysis. The invention is realized in that a power industry software provider evaluation system based on principal component analysis comprises: The system comprises a data acquisition module, an index definition module, a principal component analysis module, an evaluation calculation module and a visual display module; the data acquisition module is connected with the index definition module and the visual display module and is used for acquiring provider related data from historical provider evaluation records, purchase contracts and project delivery data sources of the power industry; The index definition module is connected with the data acquisition module, the evaluation calculation module and the visual display module and is used for containing 12 evaluation indexes of technical reserve, enterprise qualification, quality promise, financial strength and software applicability; the principal component analysis module is connected with the index definition module and the evaluation calculation module and is used for carrying out standardized processing on index data, reducing the dimension by using a principal component analysis method and extracting a few key principal components to represent the comprehensive capacity of a provider; the evaluation calculation module is connected with the index definition module, the principal component analysis module and the visual display module and is used for calculating the comprehensive score of the provider based on the principal component score; The visual display module is connected with the data acquisition module, the index definition module and the evaluation calculation module and used for displaying evaluation results and comparative analysis of all suppliers in the forms of radar graphs and bar graphs. Further, the data acquisition module: 1) And (3) data acquisition: importing provider data from a purchasing system or Excel file into a database using a database API or ETL tool; The data field comprises 12 indexes of technical reserve, enterprise qualification and quality commitment and basic information of suppliers; 2) Data cleaning: Processing the missing value in the data, namely filling, interpolating or deleting the missing record through the mean value to ensure the data integrity; Checking abnormal values of data, and identifying and processing the abnormal values through a box diagram or Z score method; 3) Data normalization: Normalizing each index according to the following formula: wherein X is an original value, mu is a mean value, sigma is a standard deviation, and X' is a standardized value. Further, the principal component analysis module: 1) Constructing a covariance matrix: Calculating covariance matrix of each index by using the normalized data: 2) Calculating eigenvalues and eigenvectors: Calculating eigenvalues and eigenvectors using linear algebraic methods or numpy.1ina1g.eig functions that call Python; 3) The main components are selected: according to the accumulated contribution rate ) Selecting a main component to enable the accumulated contribution rate to reach more than 85%; 4) Calculating the principal component score: Calculating principal component scores according to the selected feature vectors and the original data: Wherein X is standardized data, and Vj is a feature vector of a j-th principal component. Further, the evaluation calculation module: 1) And (3) comprehensive score calculation: The comprehensive score formula is: Wherein, the The score is a score of the principal component,The ratio of the characte