Enterprise operation method and system based on artificial performance analysis

Abstract

The invention provides an enterprise operation method and system based on artificial performance analysis. The method comprises the following steps: acquiring to-be-analyzed enterprise operation data at the current moment; inputting the to-be-analyzed enterprise operation data at the current moment into the artificial efficiency analysis model at the current moment to obtain an artificial efficiency analysis result at the current moment, which is output by the artificial efficiency analysis model at the current moment; the artificial efficiency analysis result at the current moment is an optimization strategy for improving the operation efficiency of the enterprise and is used for guiding the enterprise to optimize the operation efficiency; wherein the artificial performance analysis model is obtained based on training of an enterprise operation data training sample; the artificial efficiency analysis model at the current moment is a model after verification and parameter adjustment based on the artificial efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment. The method can improve the labor efficiency, reduce the labor cost and improve the enterprise competitiveness.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise operation, and provides an enterprise operation method and system based on manual efficiency analysis. Background Art

[0002] In enterprise management, labor efficiency is a key indicator for measuring the efficiency of production, operations, and management, and has a direct impact on a company's competitiveness. Traditional labor efficiency analysis methods rely primarily on the manual collection and analysis of statistical data, analyzing indicators such as the efficiency, quality, and cost of manual work, and then identifying factors affecting labor efficiency and proposing improvement measures. However, this approach has many drawbacks: first, manual collection and statistical data is labor-intensive and time-consuming; second, data quality is difficult to ensure; third, the data analysis method is limited and cannot systematically analyze the factors affecting labor efficiency; and fourth, improvement measures are difficult to accurately implement and ensure effectiveness. Therefore, a more efficient, accurate, and systematic labor efficiency analysis method is urgently needed to help enterprises optimize operational efficiency and enhance their competitiveness. Summary of the Invention

[0003] This invention provides a business operations method and system based on labor efficiency analysis, addressing the shortcomings of existing labor efficiency analysis methods, including low efficiency, poor data quality, a single analysis method, and difficulty in accurately implementing improvement measures. This invention can improve labor efficiency, reduce labor costs, and enhance business competitiveness.

[0004] The present invention provides an enterprise operation method based on human efficiency analysis, comprising: obtaining enterprise operation data to be analyzed at the current moment; inputting the enterprise operation data to be analyzed at the current moment into a human efficiency analysis model at the current moment, and obtaining a human efficiency analysis result at the current moment output by the human efficiency analysis model at the current moment; the human efficiency analysis result at the current moment is an optimization strategy for improving enterprise operation efficiency, and is used to guide the enterprise to optimize operation efficiency; wherein the human efficiency analysis model is obtained by training based on enterprise operation data training samples; the human efficiency analysis model at the current moment is a model that has been verified and adjusted based on the human efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment.

[0005] According to a method for enterprise operation based on human efficiency analysis provided by the present invention, the method inputs the enterprise operation data to be analyzed at the current moment into the human efficiency analysis model at the current moment to obtain the human efficiency analysis result output by the human efficiency analysis model at the current moment, including: inputting the enterprise operation data to be analyzed at the current moment into a preprocessing network for data preprocessing to obtain preprocessed data output by the preprocessing network; inputting the preprocessed data into a feature extraction network for feature extraction to obtain enterprise operation features output by the feature extraction network; inputting the enterprise operation features into a clustering analysis network for feature clustering analysis to obtain clustering analysis results output by the analysis network; the clustering analysis results include consistent pattern features and abnormal pattern features in the enterprise operation features; inputting the clustering analysis results into an association analysis network for feature association analysis to obtain association analysis results output by the association analysis network; the association analysis results are used to characterize association rules between features; inputting the association analysis results into a trend prediction network for trend prediction to obtain trend prediction results for future enterprise operation data output by the trend prediction network; and inputting the trend prediction results into a strategy generation network to obtain the human efficiency analysis results output by the strategy generation network.

[0006] According to an enterprise operation method based on manual efficiency analysis provided by the present invention, the preprocessing network includes a missing value processing module, an outlier processing module and a normalization processing module; the missing value processing module is used to use mean interpolation, regression interpolation or K-nearest neighbor interpolation method to process missing values ​​in the data; the outlier processing module is used to use statistical methods or machine learning algorithms to identify and process outliers in the data; the statistical method includes a 3σ principle method or a box plot method, and the machine learning algorithm includes an isolation forest algorithm or a DBSCAN algorithm; the normalization processing module is used to use Min-Max scaling or Z-score standardization method to normalize or standardize the data; the feature extraction network includes a feature selection module and a feature construction module; the feature selection module is used to select influencing features for manual efficiency analysis from the preprocessed data based on filtering, embedding or wrapping feature selection algorithms; the feature construction module is used to expand and optimize the features selected by the feature selection module through aggregation features, interactive features and dimensionality reduction technology to construct the enterprise operation features.

[0007] According to an enterprise operation method based on manual efficiency analysis provided by the present invention, the cluster analysis network is specifically used to use the K-Means clustering algorithm, the DBSCAN algorithm or the hierarchical clustering algorithm to perform cluster analysis on the enterprise operation characteristics to obtain the cluster analysis results, and use the silhouette coefficient clustering evaluation indicator to evaluate the cluster analysis results; the association analysis network is specifically used to use the Apriori algorithm to perform feature association analysis on the cluster analysis results, set support and confidence thresholds, and use Lift and chi-square test indicators to screen association rules to obtain the association analysis results.

[0008] According to an enterprise operation method based on manual efficiency analysis provided by the present invention, the trend prediction network is specifically used to use linear regression and generalized linear algorithm, support vector machine algorithm, decision tree algorithm or deep learning algorithm to analyze the association analysis results, predict the trend of the enterprise's future operation data, and obtain the trend prediction results; the strategy generation network is specifically used to perform sensitivity analysis, causal analysis and operation efficiency evaluation on the trend prediction results to obtain the manual efficiency analysis results.

[0009] According to an enterprise operation method based on labor efficiency analysis provided by the present invention, after inputting the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment and obtaining the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment, it also includes: obtaining the actual optimization strategy of the enterprise operation efficiency at the current moment; and verifying and adjusting the parameters of the labor efficiency analysis model at the current moment according to the labor efficiency analysis result at the current moment and the actual optimization strategy of the enterprise operation efficiency at the current moment to obtain the labor efficiency analysis model at the next moment.

[0010] The present invention also provides an enterprise operation system based on labor efficiency analysis, including: an enterprise operation data acquisition module, used to obtain the enterprise operation data to be analyzed at the current moment; a labor efficiency analysis module, used to input the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment, and obtain the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, and is used to guide the enterprise to optimize its operation efficiency; wherein, the labor efficiency analysis model is obtained by training based on enterprise operation data training samples; the labor efficiency analysis model at the current moment is a model that has been verified and adjusted based on the labor efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the enterprise operation method based on manual efficiency analysis as described above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described enterprise operation methods based on human efficiency analysis.

[0013] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described enterprise operation methods based on human efficiency analysis.

[0014] The present invention provides an enterprise operation method and system based on labor efficiency analysis, which obtains enterprise operation data to be analyzed at the current moment; inputs the enterprise operation data to be analyzed at the current moment into a labor efficiency analysis model at the current moment, and obtains a labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving enterprise operation efficiency, which is used to guide the enterprise to optimize operation efficiency; wherein, the labor efficiency analysis model is trained based on enterprise operation data training samples; the labor efficiency analysis model at the current moment is a model that has been verified and adjusted based on the labor efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment. The present invention can improve labor efficiency, reduce labor costs, and enhance enterprise competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 It is a flowchart of the enterprise operation method based on manual efficiency analysis provided by the present invention.

[0017] Figure 2 It is a structural diagram of the enterprise operation system based on human efficiency analysis provided by the present invention.

[0018] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0020] Labor efficiency refers to the efficiency of manual work and is usually measured by indicators such as the time and quality of manual work. Labor efficiency is an important component of enterprise management and has a direct impact on the production, operation, and management efficiency of an enterprise. The purpose of labor efficiency management is to improve labor efficiency and reduce labor costs through the analysis and evaluation of labor efficiency, thereby enhancing the competitiveness of the enterprise. At present, the main method of labor efficiency analysis is to manually collect and analyze statistical data, analyze indicators such as the efficiency, quality, and cost of manual work, identify factors affecting labor efficiency, and propose improvement measures. However, this method has some problems: first, the workload of manually collecting and analyzing statistical data is large and time-consuming; second, data quality is difficult to ensure; third, the data analysis method is single and cannot systematically analyze the factors affecting labor efficiency; fourth, improvement measures are difficult to implement accurately and it is difficult to guarantee the improvement effect.

[0021] Please refer to Figure 1 , Figure 1 This is a flow chart of the enterprise operation method based on human efficiency analysis provided by the present invention.

[0022] The present invention provides an enterprise operation method based on labor efficiency analysis, comprising: 101: Obtain the current enterprise operation data to be analyzed; 102: Input the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment, and obtain the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, which is used to guide the enterprise to optimize its operation efficiency; wherein, the labor efficiency analysis model is trained based on the enterprise operation data training sample; the labor efficiency analysis model at the current moment is a model that has been verified and adjusted based on the labor efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment.

[0023] In order to solve the technical problems existing in the prior art, the present invention provides an enterprise operation method based on manual efficiency analysis, which aims to help enterprises optimize their operational efficiency. The manual efficiency analysis model in the present invention collects and processes the enterprise's multi-dimensional operational data such as production, sales, inventory, and finance, and uses algorithms such as feature engineering, cluster analysis, and association analysis to mine the inherent laws in the data, analyze historical data, and predict future trends. The manual efficiency analysis model of the present invention helps enterprises continuously improve their operational efficiency by identifying problems and defects in operations and proposing optimization strategies, thereby realizing automated management and decision support based on artificial intelligence.

[0024] Specifically, enterprise operational data, including production data, sales data, inventory data, and financial data, is collected. This data forms the input for the labor efficiency analysis model. Enterprise operational data can come from a variety of sources, such as production equipment sensors (Internet of Things devices), ERP (Enterprise Resource Planning) systems, CRM (Customer Relationship Management) systems, financial management systems, inventory management systems, and sales records. Data sources must be diverse and consistent. Consider combining real-time data collection with historical data, with real-time data used for short-term operational optimization and historical data used for long-term trend analysis and forecasting. Collected data can be structured (such as tabular data in a database), semi-structured (such as JSON (JavaScript Object Notation) files), or unstructured (such as text and images). For different data types, corresponding collection interfaces and data format conversion tools must be designed. The labor efficiency analysis model performs data cleansing, feature extraction, cluster analysis, correlation analysis, and trend forecasting on the current enterprise operational data to be analyzed, generating optimization strategies to improve enterprise operational efficiency.

[0025] The current labor efficiency analysis model is a model that has been verified and adjusted based on the labor efficiency analysis results from the previous time step and the actual optimization strategy for the enterprise's operational efficiency. Specifically, at each time step, the labor efficiency analysis results output by the labor efficiency analysis model are compared with the actual optimization strategy for the enterprise's operational efficiency. Based on the comparison results, the labor efficiency analysis model parameters are adjusted to optimize model performance.

[0026] Enterprise operational effectiveness can be expressed as: E=f(D,A,P) Among them, E is the enterprise's operational efficiency, which is the target variable to be ultimately evaluated and optimized; D is the enterprise's operational data; A is the data analysis algorithm used to mine data rules and patterns, mainly including cluster analysis, association analysis, trend prediction and other algorithms; P is the optimization strategy for improving the enterprise's operational efficiency based on the results of manual efficiency analysis, which is used to guide enterprises in optimizing their operational efficiency.

[0027] Therefore, the artificial efficiency analysis model uses various data analysis algorithms A to analyze the enterprise operation data D, and derives optimization strategies and suggestions P to help enterprises continuously improve their operational efficiency E.

[0028] From the perspective of mathematical formulas, it can be expressed as: P=A(D), which means that the strategy P is obtained by analyzing the data D through the algorithm A; E=f(D,P) means that the enterprise operational effectiveness E is a function of data D and strategy P.

[0029] Through continuous learning and optimization of the human efficiency analysis model, A and f will continue to improve, bringing P and E increasingly into line with the company's operational objectives and achieving true AI-driven performance management. Therefore, the mathematical representation of the entire human efficiency analysis model is a continuous optimization and iteration process of the two formulas above.

[0030] Preferably, data visualization tools are used to visually display the analysis results, helping decision makers understand the model output. The human efficiency analysis model can be integrated with the company's ERP system to form a closed data loop, further improving the efficiency of data-driven decision-making.

[0031] The beneficial effects of the present invention are: By optimizing manual operation processes, labor costs can be reduced and the profitability of the enterprise can be improved.

[0032] By improving labor efficiency and reducing labor costs, the competitiveness of enterprises can be improved and they can gain an advantageous position in market competition.

[0033] Through continuous improvement of business operations, the operational efficiency and management level of the enterprise can be continuously improved, promoting the long-term development of the enterprise.

[0034] The implementation process of the present invention can stimulate the innovation awareness and innovation ability of enterprise employees, prompt the enterprise to continuously innovate in operation and management, and thus improve the overall competitiveness of the enterprise.

[0035] The enterprise operation method based on human efficiency analysis can provide enterprises with accurate and comprehensive operation data and analysis reports, helping enterprises to make decisions faster and improve their operational efficiency.

[0036] By continuously tracking and analyzing labor efficiency, companies can promptly identify potential risks, take appropriate measures to prevent them, and reduce operational risks.

[0037] The implementation process of this invention requires the use of information technology means such as data mining and data analysis, which helps to improve the informatization level of the enterprise and lay the foundation for the digital transformation of the enterprise.

[0038] The present invention can provide employees with targeted training and development opportunities based on their labor efficiency indicators and influencing factors, thereby improving their business capabilities and comprehensive qualities.

[0039] As a preferred embodiment, the enterprise operation data to be analyzed at the current moment is input into the artificial efficiency analysis model at the current moment to obtain the artificial efficiency analysis result output by the artificial efficiency analysis model at the current moment, including: inputting the enterprise operation data to be analyzed at the current moment into the preprocessing network for data preprocessing to obtain the preprocessed data output by the preprocessing network; inputting the preprocessed data into the feature extraction network for feature extraction to obtain the enterprise operation features output by the feature extraction network; inputting the enterprise operation features into the clustering analysis network for feature clustering analysis to obtain the clustering analysis results output by the analysis network; the clustering analysis results include consistent pattern features and abnormal pattern features in the enterprise operation features; inputting the clustering analysis results into the association analysis network for feature association analysis to obtain the association analysis results output by the association analysis network; the association analysis results are used to characterize the association rules between features; inputting the association analysis results into the trend prediction network for trend prediction to obtain the trend prediction results of the enterprise's future operation data output by the trend prediction network; inputting the trend prediction results into the strategy generation network to obtain the artificial efficiency analysis results output by the strategy generation network.

[0040] In this embodiment, manual labor data from enterprise operations, including indicators such as labor time, quality, and cost, is manually collected and compiled. This data reflects the efficiency and quality of the enterprise's labor operations. A preprocessing network then performs preprocessing operations such as cleaning, deduplication, and normalization on the collected data to obtain preprocessed data, ensuring data quality and consistency. Data mining and analysis techniques are employed to mine and analyze factors influencing labor efficiency from the preprocessed data using feature extraction networks, cluster analysis networks, association analysis networks, and trend prediction networks, establishing relationships between these factors and labor efficiency. These factors include labor process, personnel skills, equipment performance, and management level. The goal of optimizing labor efficiency is to improve the enterprise's labor efficiency by reducing labor time, improving labor quality, and lowering labor costs. Based on the data analysis results, specific measures for optimizing labor efficiency are proposed, such as adjusting labor process, improving labor efficiency, and enhancing personnel skills and management level. These optimization measures are applied to enterprise operations, and their effective implementation is ensured through real-time monitoring and feedback mechanisms. Based on the implementation results, continuously adjust and optimize the methods of labor efficiency analysis to adapt to changes in corporate operations.

[0041] During implementation, appropriate data collection methods, data preprocessing methods, data modeling methods, data mining methods, data analysis methods, optimization measures, and implementation and monitoring mechanisms can be selected based on the company's actual situation. In actual application, flexible adjustments and optimizations can be made based on the company's characteristics and needs.

[0042] As a preferred embodiment, the preprocessing network includes a missing value processing module, an outlier processing module and a normalization processing module; the missing value processing module is used to process missing values ​​in the data using mean interpolation, regression interpolation or K-nearest neighbor interpolation methods; the outlier processing module is used to identify and process outliers in the data using statistical methods or machine learning algorithms; the statistical methods include the 3σ principle method or the box plot method, and the machine learning algorithms include the isolation forest algorithm or the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm; the normalization processing module is used to normalize or standardize the data using the Min-Max scaling or Z-score standardization method; the feature extraction network includes a feature selection module and a feature construction module; the feature selection module is used to select influencing features for manual performance analysis from the preprocessed data based on filtering, embedding or wrapping feature selection algorithms; the feature construction module is used to expand and optimize the features selected by the feature selection module through aggregation features, interactive features and dimensionality reduction techniques to construct enterprise operation features.

[0043] In this embodiment, the preprocessing network cleans, filters, and integrates the enterprise operation data to be analyzed, processes missing values ​​and outliers, and prepares data for subsequent analysis.

[0044] Missing value processing uses mean interpolation, regression interpolation, and K-nearest neighbor interpolation methods to handle missing values ​​in the data. The specific method can be selected based on the distribution characteristics of the data.

[0045] Outlier detection uses statistical methods (such as the 3σ principle and box plots) or machine learning algorithms (such as isolation forest and DBSCAN) to identify and process outliers to prevent abnormal data from affecting the analysis results.

[0046] In order to avoid the impact caused by the dimensional difference of features, the data needs to be normalized or standardized. Methods include Min-Max scaling and Z-score standardization.

[0047] The feature extraction network mines and constructs features from the integrated data, selecting features that have a significant impact on the model. Common methods include PCA (Principal Component Analysis) and statistical feature selection.

[0048] When processing multidimensional data, the feature selection module selects meaningful features, which is the key to improving model performance. Feature selection is performed through the following methods: Filter-based feature selection: Use statistical correlation (chi-square test, Pearson correlation coefficient) for preliminary screening.

[0049] Embedding-based feature selection: Screening is performed by evaluating feature importance in models such as random forests and XGBoost.

[0050] Parcel-based feature selection: Features are selected through the recursive feature elimination (RFE) method combined with the algorithm training process.

[0051] The feature construction module uses a variety of techniques to expand the original data, such as: Aggregation features: Perform moving average, maximum, and minimum statistical operations on time series data.

[0052] Interaction features: Generate cross products, square terms, and logarithmic terms between features.

[0053] Dimensionality reduction technology: Use principal component analysis (PCA) or linear discriminant analysis (LDA) to reduce the dimension of features and retain the most explanatory features.

[0054] As a preferred embodiment, the cluster analysis network is specifically used to use the K-Means clustering algorithm, DBSCAN algorithm or hierarchical clustering algorithm to perform cluster analysis on the enterprise operation characteristics to obtain cluster analysis results, and use the silhouette coefficient clustering evaluation indicator to evaluate the cluster analysis results; the association analysis network is specifically used to use the Apriori algorithm to perform feature association analysis on the cluster analysis results, set support and confidence thresholds, and use Lift and chi-square test indicators to screen association rules to obtain association analysis results.

[0055] In this embodiment, the cluster analysis network uses a clustering algorithm such as K-means (K-Means Clustering) to perform cluster analysis on the data to identify consistent patterns and abnormal patterns in the enterprise data.

[0056] The K-Means clustering algorithm is suitable for situations where data points are spherically distributed and the number of clusters needs to be specified in advance.

[0057] The DBSCAN algorithm can discover clusters of arbitrary shapes and is suitable for data with noise.

[0058] Hierarchical clustering algorithm can flexibly select clustering structures at different levels by constructing cluster trees, and is suitable for situations with uncertain number of clusters.

[0059] The silhouette coefficient clustering evaluation indicator is used to measure the quality of the clustering results and to tune the parameters of the clustering algorithm.

[0060] The association analysis network uses association analysis algorithms such as the Apriori (Apriori Algorithm) algorithm under the MapReduce framework to mine association rules between operational data and discover the inherent connections between data.

[0061] In order to improve efficiency, the Apriori association analysis algorithm chooses a parallel or incremental implementation method.

[0062] Set reasonable support and confidence thresholds to ensure that the mined association rules have practical business significance. Too low thresholds will result in too many rules and make them difficult to interpret, while too high thresholds may ignore valuable rules.

[0063] Use Lift and Chi-square test indicators to further screen high-value association rules. When applying association rules to business decisions, verify their effectiveness through A / B testing.

[0064] As a preferred embodiment, the trend prediction network is specifically used to use linear regression and generalized linear algorithm, support vector machine algorithm, decision tree algorithm or deep learning algorithm to analyze the association analysis results, predict the trend of the company's future operating data, and obtain trend prediction results; the strategy generation network is specifically used to perform sensitivity analysis, causal analysis and operational efficiency evaluation on the trend prediction results, and obtain manual efficiency analysis results.

[0065] In this embodiment, based on the characteristics of the data and business needs, the trend prediction network selects an appropriate machine learning algorithm to analyze historical data to predict future trends.

[0066] Linear regression and generalized linear algorithms: Applicable to data with linear relationships and easy to interpret.

[0067] Support Vector Machine (SVM): Suitable for high-dimensional and nonlinear data.

[0068] Decision trees and their ensemble methods (such as random forests and XGBoost (Extreme Gradient Boosting)): They are good at handling nonlinear relationships and have high interpretability.

[0069] Deep learning algorithms: Suitable for large-scale, highly complex data sets, and often used to predict complex time series or unstructured data such as images and text.

[0070] The model's generalization ability is evaluated through cross-validation, leave-one-out validation, and rolling window validation of time series data. Evaluation metrics include RMSE (Root Mean Square Error), MAE (Mean Absolute Error), R² (Coefficient of Determination), and AUC (Area Under the Curve).

[0071] By analyzing the results of the above steps, the strategy generation network identifies problems and defects in the enterprise operation process, evaluates their impact on operational efficiency, and provides optimization suggestions.

[0072] Sensitivity analysis is used to evaluate the impact of various input variables on the final operational efficiency E to determine which factors play a key role in improving efficiency.

[0073] Causal inference techniques (such as structural equation models and causal trees) can be combined to further analyze the causal relationship between features, rather than just staying at the correlation level.

[0074] Introduce Data Envelopment Analysis (DEA) or Stochastic Frontier Analysis (SFA) tools to evaluate the relative operational efficiency of enterprises under different time periods and different decision-making situations.

[0075] As a preferred embodiment, the enterprise operation data to be analyzed at the current moment is input into the labor efficiency analysis model at the current moment, and after obtaining the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment, it also includes: obtaining the actual optimization strategy of the enterprise operation efficiency at the current moment; based on the labor efficiency analysis result at the current moment and the actual optimization strategy of the enterprise operation efficiency at the current moment, the labor efficiency analysis model at the current moment is verified and adjusted to obtain the labor efficiency analysis model at the next moment.

[0076] Feedback optimization suggestions to the enterprise, and repeat the above steps based on new data to continuously optimize and improve the labor efficiency analysis model.

[0077] Design adaptive mechanisms to enable the model to update and iteratively learn based on new data. Use online learning algorithms (such as online stochastic gradient descent and online decision trees) to process real-time updated data.

[0078] Connect the model's optimization suggestions with the company's actual business processes, automatically generate execution plans, and assist in decision-making through an intelligent decision support system (DSS).

[0079] Introducing reinforcement learning or Bayesian optimization, continuously exploring and optimizing strategy P, so that the efficiency E is gradually improved.

[0080] The labor efficiency analysis results obtained in the above manner are compared with the actual optimization strategy of the enterprise's operational efficiency, and the labor efficiency analysis model is verified and adjusted based on the comparison results.

[0081] The enterprise operation system based on human efficiency analysis provided by the present invention is described below. The enterprise operation system based on human efficiency analysis described below and the enterprise operation method based on human efficiency analysis described above can be referenced to each other.

[0082] Please refer to Figure 2 , Figure 2 This is a structural diagram of the enterprise operation system based on human efficiency analysis provided by the present invention.

[0083] The present invention also provides an enterprise operation system based on labor efficiency analysis, including: an enterprise operation data acquisition module 201, used to obtain the enterprise operation data to be analyzed at the current moment; a labor efficiency analysis module 202, used to input the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment, and obtain the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, and is used to guide the enterprise to optimize its operation efficiency; wherein, the labor efficiency analysis model is obtained by training based on enterprise operation data training samples; the labor efficiency analysis model at the current moment is a model that has been verified and adjusted based on the labor efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency.

[0084] Figure 3 The following is a schematic diagram of the structure of an electronic device, such as Figure 3As shown, the electronic device may include: a processor 301, a communications interface 302, a memory 303, and a communications bus 304, wherein the processor 301, the communications interface 302, and the memory 303 communicate with each other via the communications bus 304. The processor 301 may call logic instructions in the memory 303 to execute an enterprise operation method based on human efficiency analysis, the method comprising: obtaining enterprise operation data to be analyzed at the current moment; inputting the enterprise operation data to be analyzed at the current moment into a human efficiency analysis model at the current moment, and obtaining a human efficiency analysis result at the current moment output by the human efficiency analysis model at the current moment; the human efficiency analysis result at the current moment is an optimization strategy for improving enterprise operation efficiency, used to guide the enterprise to optimize operation efficiency; wherein the human efficiency analysis model is trained based on enterprise operation data training samples; the human efficiency analysis model at the current moment is a model that has been verified and adjusted based on the human efficiency analysis result at the previous moment and the actual optimization strategy for enterprise operation efficiency at the previous moment.

[0085] Furthermore, the logic instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the relevant art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0086] An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the enterprise operation method based on human efficiency analysis provided by the above-mentioned method embodiments, the method including: obtaining enterprise operation data to be analyzed at the current moment; inputting the enterprise operation data to be analyzed at the current moment into the human efficiency analysis model at the current moment, and obtaining the human efficiency analysis result at the current moment output by the human efficiency analysis model at the current moment; the human efficiency analysis result at the current moment is an optimization strategy for improving enterprise operation efficiency, which is used to guide the enterprise to optimize operation efficiency; wherein the human efficiency analysis model is obtained by training based on enterprise operation data training samples; the human efficiency analysis model at the current moment is a model that has been verified and adjusted based on the human efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment.

[0087] On the other hand, an embodiment of the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the enterprise operation method based on manual efficiency analysis provided in the above-mentioned embodiments, the method comprising: obtaining the enterprise operation data to be analyzed at the current moment; inputting the enterprise operation data to be analyzed at the current moment into the manual efficiency analysis model at the current moment, and obtaining the manual efficiency analysis result at the current moment output by the manual efficiency analysis model at the current moment; the manual efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, and is used to guide the enterprise to optimize its operation efficiency; wherein, the manual efficiency analysis model is obtained by training based on enterprise operation data training samples; the manual efficiency analysis model at the current moment is a model that has been verified and adjusted based on the manual efficiency analysis result at the previous moment and the actual optimization strategy of the enterprise operation efficiency at the previous moment.

[0088] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0089] Through the description of the above embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the relevant technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0090] 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An enterprise operation method based on labor efficiency analysis, characterized in that: include: Obtain the current enterprise operation data to be analyzed; Inputting the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment, obtaining a labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, which is used to guide the enterprise to optimize its operation efficiency; Wherein, the labor efficiency analysis model is obtained by training based on enterprise operation data training samples; The current labor efficiency analysis model is a model that has been verified and adjusted based on the labor efficiency analysis results of the previous moment and the actual optimization strategy of the enterprise operation efficiency of the previous moment.

2. The enterprise operation method based on labor efficiency analysis according to claim 1, characterized in that: The step of inputting the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment to obtain the labor efficiency analysis result output by the labor efficiency analysis model at the current moment includes: Inputting the enterprise operation data to be analyzed at the current moment into a preprocessing network for data preprocessing, and obtaining preprocessed data output by the preprocessing network; Inputting the preprocessed data into a feature extraction network for feature extraction, and obtaining enterprise operation features output by the feature extraction network; Inputting the enterprise operation characteristics into a cluster analysis network to perform feature cluster analysis, and obtaining cluster analysis results output by the analysis network; the cluster analysis results include consistent pattern characteristics and abnormal pattern characteristics in the enterprise operation characteristics; Inputting the cluster analysis results into an association analysis network to perform feature association analysis, and obtaining an association analysis result output by the association analysis network; the association analysis result is used to characterize association rules between features; Inputting the correlation analysis results into a trend prediction network for trend prediction, and obtaining a trend prediction result of the enterprise's future operating data output by the trend prediction network; The trend prediction result is input into a strategy generation network to obtain the artificial effectiveness analysis result output by the strategy generation network.

3. The enterprise operation method based on labor efficiency analysis according to claim 2, characterized in that: The preprocessing network includes a missing value processing module, an outlier processing module and a normalization processing module; The missing value processing module is used to process missing values ​​in the data using mean interpolation, regression interpolation or K-nearest neighbor interpolation method; The outlier processing module is used to identify and process outliers in the data using a statistical method or a machine learning algorithm; the statistical method includes a 3σ principle method or a box plot method, and the machine learning algorithm includes an isolation forest algorithm or a DBSCAN algorithm; The normalization processing module is used to normalize or standardize the data using Min-Max scaling or Z-score standardization method; The feature extraction network includes a feature selection module and a feature construction module; The feature selection module is used to select influencing features for human efficiency analysis from the pre-processed data based on filtering, embedding or wrapping feature selection algorithms; The feature construction module is used to expand and optimize the features selected by the feature selection module through aggregation features, interactive features and dimensionality reduction technology to construct the enterprise operation features.

4. The enterprise operation method based on labor efficiency analysis according to claim 2, characterized in that: The cluster analysis network is specifically used to perform cluster analysis on the enterprise operation characteristics using a K-Means clustering algorithm, a DBSCAN algorithm or a hierarchical clustering algorithm to obtain the cluster analysis results, and evaluate the cluster analysis results using a silhouette coefficient cluster evaluation indicator; The association analysis network is specifically used to perform feature association analysis on the cluster analysis results using the Apriori algorithm, set support and confidence thresholds, and use Lift and chi-square test indicators to screen association rules to obtain the association analysis results.

5. The enterprise operation method based on labor efficiency analysis according to claim 2, characterized in that: The trend prediction network is specifically used to analyze the association analysis results using linear regression and generalized linear algorithms, support vector machine algorithms, decision tree algorithms or deep learning algorithms, to predict the trend of the enterprise's future operating data and obtain the trend prediction results; The strategy generation network is specifically used to perform sensitivity analysis, causal analysis and operational efficiency evaluation on the trend prediction results, and obtain the manual efficiency analysis results.

6. The enterprise operation method based on labor efficiency analysis according to any one of claims 1 to 5, characterized in that: After inputting the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment and obtaining the labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment, the method further includes: Obtain the actual optimization strategy for the current enterprise operational efficiency; According to the labor efficiency analysis result at the current moment and the actual optimization strategy of the enterprise operation efficiency at the current moment, the labor efficiency analysis model at the current moment is verified and adjusted to obtain the labor efficiency analysis model at the next moment.

7. An enterprise operation system based on labor efficiency analysis, characterized in that: include: Enterprise operation data acquisition module, used to obtain the enterprise operation data to be analyzed at the current moment; A labor efficiency analysis module is configured to input the enterprise operation data to be analyzed at the current moment into the labor efficiency analysis model at the current moment, and obtain a labor efficiency analysis result at the current moment output by the labor efficiency analysis model at the current moment; the labor efficiency analysis result at the current moment is an optimization strategy for improving the enterprise operation efficiency, and is used to guide the enterprise to optimize its operation efficiency; Wherein, the labor efficiency analysis model is obtained by training based on enterprise operation data training samples; The current labor efficiency analysis model is a model that has been verified and adjusted based on the labor efficiency analysis results of the previous moment and the actual optimization strategy of the enterprise's operational efficiency.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the enterprise operation method based on human efficiency analysis as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the enterprise operation method based on human efficiency analysis as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the enterprise operation method based on human efficiency analysis as claimed in any one of claims 1 to 6 is implemented.

Images