Research on Electricity Marketing Inspection Methods Applying RPA Informationization Intelligent Management Technology
Bibliographic record
Abstract
Robotic process automation (RPA) technology along with the rapid development of information technology is increasingly widely used in various industries. This paper mainly explores its application in the field of electric power, and utilizes RPA technology to improve the quality and efficiency of power marketing audit. In order to solve the data anomaly problem in the process of power marketing audit, this paper adopts K-means algorithm to cluster the anomalous data, and combines with the correlation calculation to realize the identification and monitoring of the anomalous data of power marketing audit. Applying RPA technology to intelligent power marketing audit, we learn the normal pattern of data by training the self-encoder network, and correct or reject the abnormal data monitored. Reinforcement learning is used to optimize the audit strategy of RPA technology, and the efficiency of the audit is improved by maximizing the cumulative rewards. The application of RPA technology significantly improves the efficiency and accuracy of the overdue prediction and the work order generation and dispatching in the electric power marketing audit, in which the average working time of the overdue prediction work is reduced by 94.92% after the application of RPA technology, the average accuracy is improved by 21.80%, and the average working time of the work order generation and dispatching process is reduced by 21.80%, and the average working time of the work order generation and dispatching process is improved by 21.80%. The average working time of work order generation and dispatching process is reduced by 97.99% and the average accuracy rate is increased by 14.54%. The application of RPA technology effectively improves the efficiency and quality of power marketing audit.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".