System and method for analyzing productivity based on electric power data

Abstract

The invention discloses a system and a method for analyzing productivity based on electric power data, and relates to the technical field of electric power data analysis. According to the method, data such as monthly electricity consumption, output values, energy consumption and the number of employees of each sub-industry are collected, and a time sequence data set is constructed after the data are cleaned and arranged; the analysis model is used for mining the relevance between electric power and enterprise data, calculating the power utilization efficiency of the high-end equipment manufacturing industry and the traditional equipment manufacturing industry, comprehensively generating the power utilization rate ratio, calculating the power utilization efficiency, the energy consumption ratio and the labor efficiency of each sub-industry, and comprehensively generating the comprehensive index of each sub-industry. In the data evaluation stage, the efficiency and energy utilization condition of the sub-industry are deeply analyzed through three evaluation units, and the power utilization rate ratio of the high-end equipment manufacturing industry and the traditional equipment manufacturing industry is evaluated. And finally, predicting future power demand and productivity development of the sub-industry through a prediction module, organizing the future power demand and productivity development into a report, and proposing specific suggestions and improvement measures.

Description

Technical Field

[0001] The present invention relates to the technical field of power data analysis, and in particular to a system and method for analyzing productivity based on power data. Background Art

[0002] Power data analysis requires a wide range of data sources, and data acquisition is complex. The data formats, update frequencies, and accuracy of these data sources vary, which increases the complexity and difficulty of data collection. Data collected from multiple channels often contain duplications, errors, and invalidity. Different data sources may also have different values ​​for the same data, which need to be processed. The analysis of productivity usually involves power data over a long period of time, and it is difficult to collect and integrate these complex data. In order to comprehensively evaluate productivity, it is necessary to calculate indicators in multiple dimensions. The calculation of these indicators involves complex mathematical formulas and algorithms, which places high demands on the professional ability and technical level of analysts. Analyzing historical data to predict future trends is a huge workload. The analysis of productivity not only involves power data, but is also closely related to knowledge in multiple disciplines such as information technology, communication technology, and artificial intelligence, requiring interdisciplinary knowledge to cope with complex analysis tasks. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a system and method for analyzing productivity based on power data. By collecting data such as monthly power consumption, output value, energy consumption and number of employees of each sub-industry, a formula is established to clean and organize the data, and then a time series data set is constructed to facilitate the management of data with a long time span; the analysis model is then used to deeply mine and calculate the power efficiency of high-end equipment manufacturing and traditional equipment manufacturing, and a power consumption rate ratio is comprehensively generated; the power efficiency, energy consumption ratio and labor efficiency of each sub-industry are calculated, and a comprehensive index of each sub-industry is comprehensively generated; the efficiency and energy utilization of the sub-industry are comprehensively evaluated and analyzed through three evaluation units, and the power consumption rate ratio of high-end and traditional equipment manufacturing industries is evaluated; the future power demand and productivity development trend of each sub-industry are predicted using a trained prediction module.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0005] A system for analyzing productivity based on power data, comprising:

[0006] Sub-industry data collection module: extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources and number of employees for five years according to sub-industry classification;

[0007] Data processing module: cleans and organizes the collected data, removes duplicate, erroneous and invalid data, and takes the average value after removing the maximum and minimum values ​​of the same data x obtained from various websites if the values ​​are different. The processed data is used to construct a time series sub-industry data set;

[0008] Data analysis module: used to establish a time series analysis model, and calculate the power consumption per unit output value of the j-th sub-industry based on the time series sub-industry data set, that is, the power efficiency of the j-th sub-industry Hyydxl j ; Classify the sub-industries into high-end equipment manufacturing and traditional equipment manufacturing, calculate the electricity efficiency of high-end equipment manufacturing Gdxl and traditional equipment manufacturing Ctxl; calculate the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j :

[0009] Evaluation module: If the comprehensive index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q1, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j < comprehensive threshold Q1, indicating that the j-th sub-industry does not belong to the green, advanced and efficient industry, sends the first warning instruction, and further calculates the power efficiency Hyydxl of the j-th sub-industry j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments of the j-th sub-industry issues, compare and analyze them with the corresponding thresholds, trigger corresponding warning instructions, and generate corresponding strategies; evaluate the ratio of electricity efficiency of high-end equipment manufacturing industry to that of traditional equipment manufacturing industry: electricity rate ratio, and analyze the differences in technology level and energy utilization efficiency between high-end equipment manufacturing industry and traditional equipment manufacturing industry;

[0010] Prediction module: Use machine learning and deep learning algorithms to predict and evaluate the future electricity demand and productivity development of each sub-industry. Before conducting the prediction and evaluation, the collected and sorted historical data and current trend data of each sub-industry are input into the prediction module for training.

[0011] Preferably, the productivity includes: new generation information technology, biotechnology, new energy, new materials, high-end equipment, new energy vehicles, green environmental protection, civil aviation, shipbuilding and marine engineering equipment, artificial intelligence, quantum information, mobile communications, the Internet of Things and blockchain.

[0012] Preferably, the same data x, if the values ​​are different, is standardized by the following formula:

[0013]

[0014] In the formula, i = 1, 2, 3, ..., n, i represents the sequence number of the same data captured on the i-th website, n represents the total number of the same data captured on n different websites, x i represents the same data value captured on the i-th website, x max represents the maximum value of the same data captured on n different websites, x min Represents the minimum value of the same data crawled from n different websites.

[0015] Preferably, the data analysis module is used to establish a time series analysis model, including a first calculation unit, which is used to calculate and obtain the electricity efficiency Hyydxl of the j-th sub-industry based on the time series sub-industry data set: j , the electricity consumption efficiency of high-end equipment manufacturing industry Gdxl and the electricity consumption efficiency of traditional equipment manufacturing industry Ctxl;

[0016] The electricity efficiency of the j-th sub-industry is Hyydxl j Calculate using the following formula:

[0017]

[0018] In the formula, j represents the sub-industry number, k = 1, 2, 3, ..., m, k represents the month number of the data, m represents the total number of months for which the data of the past m months are obtained, Q(j, k) represents the monthly electricity consumption of the j-th sub-industry in the k-th month, and P(j, k) represents the monthly output value of the j-th sub-industry in the k-th month;

[0019] The electricity efficiency of the high-end equipment manufacturing industry Gdxl is calculated by the following formula:

[0020]

[0021] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which the data is obtained, m represents the total number of months for which the data for the past m months is obtained, g = 1, 2, 3, ..., s, g represents the serial number of the high-end equipment manufacturing industry, s represents the total number of high-end equipment manufacturing industries, Q(g, k) represents the monthly electricity consumption of the g-th high-end equipment manufacturing industry in the k-th month, Q(g, k) represents the monthly output value of the g-th high-end equipment manufacturing industry in the k-th month, represents the total monthly electricity consumption of all s high-end equipment manufacturing industries in a total of m months. It represents the monthly output value of all s high-end equipment manufacturing industries in a total of m months;

[0022] The electricity consumption efficiency Ctxl of the traditional equipment manufacturing industry is calculated by the following formula:

[0023]

[0024] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for obtaining data, m represents the total number of months for obtaining data for the past m months, c = 1, 2, 3, ..., s, c represents the serial number of the traditional equipment manufacturing industry, q represents the total number of traditional equipment manufacturing industries, Q(c, k) represents the monthly electricity consumption of the cth traditional equipment manufacturing industry in the kth month, Q(c, k) represents the monthly output value of the cth traditional equipment manufacturing industry in the kth month, represents the total monthly electricity consumption of all q traditional equipment manufacturing industries in m months. It represents the monthly output value of all q traditional equipment manufacturing industries in a total of m months.

[0025] Preferably, the data analysis module further includes a second calculation unit, which is used to calculate and obtain: the consumption ratio Nybl of the yth energy of the jth sub-industry according to the time series sub-industry data set jy and the consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy , because the measurement units of various energy sources are different, according to the conversion coefficients of energy types issued by the energy management department, the consumption of various energy sources is first converted into the consumption of standard coal, and then the calculation is performed;

[0026] The consumption ratio of the yth energy source in the jth sub-industry is Nybl jy Calculate using the following formula:

[0027]

[0028] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data of the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, N(j, k, y) represents the consumption of the yth type of energy in the kth month of the jth sub-industry, It represents the consumption of the yth type of energy in the jth sub-industry in m months. It represents the consumption of all t types of energy in the j-th sub-industry in m months;

[0029] The consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy Calculate using the following formula:

[0030]

[0031] Where, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data for the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, f = 1, 2, 3, ..., u, f represents the serial number of different types of green energy, u represents the total number of green energy types, N(j, k, f) represents the f-th green energy consumption of the j-th sub-industry in the k-th month, N(j, k, y) represents the y-th energy consumption of the j-th sub-industry in the k-th month, represents the consumption of all u types of green energy in the j-th sub-industry in m months, It represents the consumption of all t types of energy in the j-th sub-industry within m months.

[0032] Preferably, the data analysis module further includes a third calculation unit, which is used to calculate and obtain the labor efficiency Rgxl of the j-th sub-industry according to the time series sub-industry data set. j , the labor efficiency of the j-th sub-industry is Rgxl j Calculate using the following formula:

[0033]

[0034] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which data is obtained, m represents the total number of months for which data for the past m months is obtained, Q(j, k) represents the monthly output value of the j-th sub-industry in the k-th month, It represents the total output value of the j-th sub-industry for m months, and Rs(j,k) represents the number of employees in the j-th sub-industry in the k-th month.

[0035] Preferably, the data analysis module further includes a first correlation unit and a second correlation unit, wherein the first correlation unit is used to convert the electricity efficiency Hyydxl of the j-th sub-industry into j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j After dimensionless processing, the following correlation formula is used to generate the comprehensive index Zhzs of the j-th sub-industry: j :

[0036] Zhz j =γ1*Hyydxl j +γ2*Lsbl jfy +γ3*Rgxl j +A1

[0037] Where γ1, γ2 and γ3 represent the electricity efficiency of the j-th sub-industry, Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The weight value is adjusted and set by the user, 0<γ1<1, 0<γ2<1, 0<γ3<1, γ1+γ2+γ3=1, A1 represents the first correction constant value;

[0038] The second correlation unit generates the ratio of the electricity consumption efficiency of the high-end equipment manufacturing industry to the electricity consumption efficiency of the traditional equipment manufacturing industry through the following correlation formula: electricity consumption rate ratio Ydlb:

[0039]

[0040] Where Gdxl is the electricity consumption efficiency of high-end equipment manufacturing industry, and Ctxl is the electricity consumption efficiency of traditional equipment manufacturing industry.

[0041] Preferably, the evaluation module includes a first evaluation unit, a second evaluation unit and a third evaluation unit;

[0042] The first evaluation unit is used to compare and evaluate the ratio of the power consumption efficiency of the high-end equipment manufacturing industry to the power consumption efficiency of the traditional equipment manufacturing industry: the power consumption rate ratio Ydlb and the power consumption rate ratio threshold Q1, and obtain a first evaluation result, including:

[0043] If the electricity consumption ratio Ydlb>Q1, it means that the electricity consumption efficiency control of high-end equipment manufacturing industry is far ahead of that of traditional equipment manufacturing industry. It is worth learning from the advanced achievements of high-end equipment manufacturing industry to upgrade and transform traditional equipment manufacturing industry.

[0044] If 1<power consumption ratio Ydlb≤Q1, it means that the power consumption efficiency of high-end equipment manufacturing industry is ahead of that of traditional equipment manufacturing industry, and the power consumption efficiency control is not obvious. It is necessary to analyze the reasons, ensure R&D investment, and further upgrade and transform the high-end equipment manufacturing industry;

[0045] If the electricity consumption rate ratio Ydlb≤1, it means that the electricity consumption efficiency of the high-end equipment manufacturing industry is lower than that of the traditional equipment manufacturing industry. It is necessary to conduct on-site investigation, find out the reasons, replace advanced equipment, and further transform and upgrade the high-end equipment manufacturing industry.

[0046] The second evaluation unit is used to convert the j-th sub-industry comprehensive index Zhzs j Compare and evaluate with the comprehensive threshold Q2 to obtain a second evaluation result, including:

[0047] If the composite index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q2, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j <Comprehensive threshold Q2 indicates that the j-th sub-industry does not belong to the green, advanced and efficient industry, and sends the first early warning instruction to remind the j-th sub-industry that it needs to be transformed and upgraded. At the same time, the third evaluation unit is triggered through the j-th sub-industry electricity efficiency Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessment of the j-type sub-industry issues and obtain the third assessment results, including:

[0048] If the electricity efficiency of the j-th sub-industry is Hyydxl j ≥ power efficiency threshold Q3, indicating that the j-th sub-industry is highly efficient in power consumption and belongs to an advanced industry. If the power consumption efficiency of the j-th sub-industry is Hyydxl j <The power efficiency threshold Q3 indicates that the j-th sub-industry is inefficient in power consumption and belongs to a backward industry. The second warning instruction is issued and a strategy is generated: the power facilities of the j-th sub-industry are upgraded to ensure efficient power consumption;

[0049] If the consumption ratio of the fth green energy in the jth sub-industry is Lsbl jfy ≥ green energy threshold Q4, indicating that the j-th sub-industry belongs to the green environmental protection industry. If the consumption ratio of the f-th green energy in the j-th sub-industry is Lsbl jfy <Green energy threshold Q4, indicating that the j-th sub-industry relies on traditional fossil energy and does not belong to the green environmental protection industry, and the third warning instruction is issued, and the strategy is generated: upgrade and transform the j-th sub-industry to rely on green energy for production;

[0050] If the labor efficiency of the j-th sub-industry is Rgxlj ≥ labor efficiency threshold Q5, indicating that the j-th sub-industry has excellent automation and belongs to a high-efficiency industry. If the labor efficiency of the j-th sub-industry is Rgxl j <The labor efficiency threshold Q5 indicates that the automation level of the j-th sub-industry is unqualified and it is an inefficient industry. The fourth early warning instruction is issued and a strategy is generated: the automation level of the j-th sub-industry is upgraded to achieve reduction in staff and increase in efficiency.

[0051] A method for analyzing productivity based on power data, comprising the following steps:

[0052] Step 1: Industry data collection: Use data crawler technology to collect data through official websites and commercial data analysis websites, and extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources, and number of employees for five years according to sub-industry classification;

[0053] Step 2: Data processing: Clean and organize the collected data, remove duplicate, erroneous and invalid data, ensure the accuracy and completeness of the data, and use the processed data to construct a time series sub-industry data set;

[0054] Step 3: Data analysis: Use the pre-established time series analysis model to conduct in-depth analysis of power data and enterprise data to mine the correlation and trend information; calculate the power efficiency of the j-th sub-industry based on the time series sub-industry data set. j , obtain the electricity efficiency of high-end equipment manufacturing industry Gdxl, the electricity efficiency of traditional equipment manufacturing industry Ctxl, and the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j , the electricity consumption efficiency Gdxl of high-end equipment manufacturing industry and the electricity consumption efficiency Ctxl of traditional equipment manufacturing industry are correlated to generate the electricity consumption rate ratio Ydlb;

[0055] Step 4: Data evaluation: The first evaluation unit evaluates the ratio of the electricity efficiency of the high-end equipment manufacturing industry to the electricity efficiency of the traditional equipment manufacturing industry: the electricity rate ratio Ydlb;

[0056] The second evaluation unit's comprehensive index of the j-th sub-industry is Zhzs jThe third evaluation unit is evaluated through the electricity efficiency of the j-type sub-industry Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments on the j-th sub-industry issues and obtain corresponding assessment results and corresponding strategies;

[0057] Step 5: Trend Forecasting: Based on historical data and current trends, use machine learning and deep learning algorithms to forecast and assess future electricity demand and productivity development in each sub-sector;

[0058] Step 6. Organize the analysis and evaluation results into a report, put forward specific suggestions and improvement measures, and predict the future development trends of each sub-industry.

[0059] The present invention has the following beneficial effects:

[0060] (1) Step 1 of the present invention collects data such as monthly electricity consumption, output value, energy consumption and number of employees of each sub-industry, quickly and efficiently obtains multi-source data, and conducts comparative analysis to obtain more accurate and rich data resources.

[0061] (2) Formulas are established to clean and organize the collected data, remove duplicate, erroneous, and invalid data, and for the same data x obtained from different websites, if the values ​​are different, the maximum and minimum values ​​are removed and the average value is taken to enhance data accuracy. The processed data is used to construct a time series sub-industry data set to facilitate the management of data with a long time span.

[0062] (3) The analytical model is used to deeply mine and calculate the electricity efficiency of high-end equipment manufacturing and traditional equipment manufacturing, and calculate indicators of multiple dimensions of each sub-industry: electricity efficiency, energy consumption ratio and labor efficiency, and comprehensively generate a comprehensive index for each sub-industry. Through three evaluation units, the efficiency and energy utilization of sub-industries are comprehensively evaluated and analyzed from multiple angles, and the electricity efficiency of high-end and traditional equipment manufacturing industries is compared, and productivity is comprehensively evaluated.

[0063] (4) Use the trained prediction module to predict the future electricity demand and productivity development trends of each sub-industry, save manpower, and make predictions quickly and accurately, which can guide the healthy development of each sub-industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a schematic diagram of a system block diagram and flow chart of productivity analysis based on power data of the present invention;

[0065] Figure 2 A schematic diagram of the steps of a method for analyzing productivity based on power data according to the present invention;

[0066] Figure 3 The present invention is a schematic diagram of a device for analyzing productivity based on power data. DETAILED DESCRIPTION

[0067] 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 only 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.

[0068] Example 1

[0069] See also Figure 1 Specifically, a system for analyzing productivity based on power data includes:

[0070] Sub-industry data collection module: extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources and number of employees for five years according to sub-industry classification; data extraction can be obtained from relevant competent authorities, or data can be collected through official websites and commercial data analysis websites using data crawler technology, traversing web pages and grabbing data on the pages.

[0071] Data processing module: cleans and organizes the collected data, removes duplicate, erroneous and invalid data, and takes the average value after removing the maximum and minimum values ​​of the same data x obtained from various websites if the values ​​are different. The processed data is used to construct a time series sub-industry data set;

[0072] Data analysis module: used to establish a time series analysis model, and calculate the power consumption per unit output value of the j-th sub-industry based on the time series sub-industry data set, that is, the power efficiency of the j-th sub-industry Hyydxl j ; Classify the sub-industries into high-end equipment manufacturing and traditional equipment manufacturing, calculate the electricity efficiency of high-end equipment manufacturing Gdxl and traditional equipment manufacturing Ctxl; calculate the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j :

[0073] Evaluation module: If the comprehensive index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q1, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j < comprehensive threshold Q1, indicating that the j-th sub-industry does not belong to the green, advanced and efficient industry, sends the first warning instruction, and further calculates the power efficiency Hyydxl of the j-th sub-industry j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments of the j-th sub-industry issues, compare and analyze them with the corresponding thresholds, trigger corresponding warning instructions, and generate corresponding strategies; evaluate the ratio of electricity efficiency of high-end equipment manufacturing industry to that of traditional equipment manufacturing industry: electricity rate ratio, and analyze the differences in technology level and energy utilization efficiency between high-end equipment manufacturing industry and traditional equipment manufacturing industry;

[0074] Prediction module: Use machine learning and deep learning algorithms to predict and evaluate the future electricity demand and productivity development of each sub-industry. Before conducting the prediction and evaluation, the collected and sorted historical data and current trend data of each sub-industry are input into the prediction module for training.

[0075] In this embodiment, the system collects data such as monthly electricity consumption, output value, energy consumption and number of employees of each sub-industry, quickly and efficiently, obtains multi-source data, and conducts comparative analysis to obtain more accurate and rich data resources. Formulas are established to clean and organize the collected data, remove duplicate, erroneous and invalid data, and process the same data from different sources, such as different values, by removing the maximum and minimum values ​​and taking the average value to enhance data accuracy. The processed data is used to construct a time series sub-industry data set, which is convenient for managing data with a long span. The analysis model is used to deeply mine and calculate the electricity efficiency of high-end equipment manufacturing and traditional equipment manufacturing industries, calculate indicators of multiple dimensions of each sub-industry: electricity efficiency, energy consumption ratio and labor efficiency, and comprehensively generate a comprehensive index for each sub-industry. Through three evaluation units, the efficiency and energy utilization of sub-industries are comprehensively evaluated and analyzed from multiple angles, and the ratio of electricity efficiency of high-end equipment manufacturing industry to electricity efficiency of traditional equipment manufacturing industry is compared, and productivity is comprehensively evaluated. The trained prediction module is used to predict the future electricity demand and productivity development trend of each sub-industry, saving manpower, and the prediction is fast and accurate, which can guide the healthy development of each sub-industry. Through comprehensive data collection, precise data processing, in-depth data analysis and scientific evaluation and prediction, this system provides strong technical support and decision-making basis for improving the production efficiency and energy utilization efficiency of various sub-industries.

[0076] Example 2

[0077] See also Figure 1 Specifically, the productivity includes: new generation information technology, biotechnology, new energy, new materials, high-end equipment, new energy vehicles, green environmental protection, civil aviation, ship and marine engineering equipment, artificial intelligence, quantum information, mobile communications, the Internet of Things and blockchain.

[0078] In this embodiment, productivity is stimulated by revolutionary technological breakthroughs, innovative allocation of production factors, and deep transformation and upgrading of industries, including: new generation information technology, biotechnology, new energy, new materials, high-end equipment, new energy vehicles, green environmental protection, civil aviation, shipbuilding and marine engineering equipment, artificial intelligence, quantum information, mobile communications, the Internet of Things, and blockchain.

[0079] Example 3

[0080] See also Figure 1 Specifically, if the values ​​of the same data x are different, they are standardized by the following formula:

[0081]

[0082] In the formula, i = 1, 2, 3, ..., n, i represents the sequence number of the same data captured on the i-th website, n represents the total number of the same data captured on n different websites, x i represents the same data value captured on the i-th website, x max represents the maximum value of the same data captured on n different websites, x min Represents the minimum value of the same data crawled from n different websites.

[0083] In this embodiment, when the numerical values ​​of the same data from different sources are different, the method of removing the maximum and minimum values ​​and taking the average value is adopted to enhance the data accuracy and lay a good data foundation for constructing the time series sub-industry data set.

[0084] Example 4

[0085] See also Figure 1 Specifically, the data analysis module is used to establish a time series analysis model, including a first calculation unit, which is used to calculate and obtain the electricity efficiency Hyydxl of the j-th sub-industry based on the time series sub-industry data set: j , the electricity consumption efficiency of high-end equipment manufacturing industry Gdxl and the electricity consumption efficiency of traditional equipment manufacturing industry Ctxl;

[0086] The electricity efficiency of the j-th sub-industry is Hyydxl j Calculate using the following formula:

[0087]

[0088] In the formula, j represents the sub-industry number, k = 1, 2, 3, ..., m, k represents the month number of the data, m represents the total number of months for which the data of the past m months are obtained, Q(j, k) represents the monthly electricity consumption of the j-th sub-industry in the k-th month, and P(j, k) represents the monthly output value of the j-th sub-industry in the k-th month;

[0089] The electricity efficiency of the high-end equipment manufacturing industry Gdxl is calculated by the following formula:

[0090]

[0091] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which the data is obtained, m represents the total number of months for which the data for the past m months is obtained, g = 1, 2, 3, ..., s, g represents the serial number of the high-end equipment manufacturing industry, s represents the total number of high-end equipment manufacturing industries, Q(g, k) represents the monthly electricity consumption of the g-th high-end equipment manufacturing industry in the k-th month, Q(g, k) represents the monthly output value of the g-th high-end equipment manufacturing industry in the k-th month, represents the total monthly electricity consumption of all s high-end equipment manufacturing industries in a total of m months. It represents the monthly output value of all s high-end equipment manufacturing industries in a total of m months;

[0092] The electricity consumption efficiency Ctxl of the traditional equipment manufacturing industry is calculated by the following formula:

[0093]

[0094] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data of the past m months is obtained, c = 1, 2, 3, ..., s, c represents the serial number of the traditional equipment manufacturing industry, q represents the total number of traditional equipment manufacturing industries, Q(c, k) represents the monthly electricity consumption of the cth traditional equipment manufacturing industry in the kth month, Q(c, k) represents the monthly output value of the cth traditional equipment manufacturing industry in the kth month, represents the total monthly electricity consumption of all q traditional equipment manufacturing industries in m months. It represents the monthly output value of all q traditional equipment manufacturing industries in a total of m months.

[0095] In this embodiment, a time series analysis model is constructed to collect and process the data of the time series sub-industry data set, especially the data related to the industry's electricity consumption and output value. This is to evaluate the electricity efficiency of different industries, especially sub-industries, high-end equipment manufacturing, and traditional equipment manufacturing. This analysis is of great significance for understanding energy utilization efficiency, industry development trends, and guiding the healthy development of each sub-industry.

[0096] The first calculation unit is the core part of the data analysis module, which is responsible for calculating the electricity efficiency of different industries based on the provided time series sub-industry data set, as follows:

[0097] Electricity efficiency of the j-th sub-industry Hyydxlj: This indicator measures the electricity efficiency of a specific sub-industry (indicated by serial number j). The average electricity efficiency during the entire analysis period is obtained by calculating the ratio of the sum of the electricity consumption of the sub-industry for m months to the monthly output value of m months.

[0098] Electricity efficiency of high-end equipment manufacturing industry Gdxl: This indicator measures the electricity efficiency of the entire high-end equipment manufacturing industry. By calculating the ratio of total electricity consumption of all high-end equipment manufacturing industries for m months to total output value for m months, the average electricity efficiency of the entire high-end equipment manufacturing industry is obtained.

[0099] Electricity efficiency of traditional equipment manufacturing industry Ctxl: This indicator measures the electricity efficiency of traditional equipment manufacturing industry. By calculating the ratio of total electricity consumption of all traditional equipment manufacturing industries in m months to total output value in m months, the average electricity efficiency of the entire traditional equipment manufacturing industry is obtained.

[0100] These calculations provide decision makers with key energy efficiency indicators to help them understand how different industries (especially the equipment manufacturing industry) perform in terms of energy use. By comparing the power efficiency between different industries or sub-industries, potential optimization space for energy use can be identified, thereby promoting energy conservation, emission reduction and sustainable development.

[0101] Example 5

[0102] See also Figure 1 Specifically, the data analysis module further includes a second calculation unit, which is used to calculate and obtain: the consumption ratio Nybl of the yth energy of the jth sub-industry according to the time series sub-industry data set jy and the consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy , because the measurement units of various energy sources are different, according to the conversion coefficients of energy types issued by the energy management department, the consumption of various energy sources is first converted into the consumption of standard coal, and then the calculation is performed;

[0103] The consumption ratio of the yth energy source in the jth sub-industry is Nybl jy Calculate using the following formula:

[0104]

[0105] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data of the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, N(j, k, y) represents the consumption of the yth type of energy in the kth month of the jth sub-industry, It represents the consumption of the yth type of energy in the jth sub-industry in m months. It represents the consumption of all t types of energy in the j-th sub-industry in m months;

[0106] The consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy Calculate using the following formula:

[0107]

[0108] Where, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data for the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, f = 1, 2, 3, ..., u, f represents the serial number of different types of green energy, u represents the total number of green energy types, N(j, k, f) represents the f-th green energy consumption of the j-th sub-industry in the k-th month, N(j, k, y) represents the y-th energy consumption of the j-th sub-industry in the k-th month, represents the consumption of all u types of green energy in the j-th sub-industry in m months, It represents the consumption of all t types of energy in the j-th sub-industry within m months.

[0109] In this embodiment, the content further expands the function of the data analysis module, introduces a second calculation unit, and focuses on calculating the consumption ratio of various energy sources and green energy consumption ratio of each sub-industry. This analysis is of great significance for understanding the energy structure of the industry, optimizing energy use, and promoting the development of green energy.

[0110] The second calculation unit uses the time series sub-industry data set and obtains two key indicators through a series of calculation steps: the consumption ratio of the yth energy in the jth sub-industry (Nybl jy ) and the consumption ratio of the yth green energy in the jth sub-industry (Lsbl jfy ). Since different energy sources have different measurement units, in order to make a unified comparison and analysis, it is first necessary to convert the consumption of these energies into the consumption of standard coal, which is done based on the energy type conversion coefficient issued by the energy management department.

[0111] The consumption ratio of the yth energy in the jth sub-industry Nybljy: This indicator reflects the consumption distribution of various energy sources in the jth sub-industry over a period of time (m months). By calculating the proportion of each energy in the total energy consumption, the consumption ratio of various energy sources in the sub-industry can be obtained. This ratio helps to understand the energy consumption structure of the sub-industry and provide data support for energy management and optimization.

[0112] The consumption ratio of the fth type of green energy in the jth sub-industry Lsbljfy: This indicator further refines the calculation of the energy consumption ratio, with a special focus on the consumption of green energy. By calculating the proportion of green energy in the total energy consumption, the performance of the sub-industry in the use of green energy can be evaluated, providing data support for promoting the development of green energy.

[0113] The calculation results of the second calculation unit are of great reference value to energy management departments, industry associations and enterprises themselves. By understanding the consumption ratio of various energy sources and green energy in each sub-industry, more scientific and reasonable energy management strategies can be formulated to optimize the energy structure, improve energy utilization efficiency, reduce environmental pollution, promote sustainable development, and help promote the green development of the entire industry.

[0114] Example 6

[0115] See also Figure 1 Specifically, the data analysis module further includes a third calculation unit, which is used to calculate and obtain the labor efficiency Rgxl of the j-th sub-industry based on the time series sub-industry data set. j , the labor efficiency of the j-th sub-industry is Rgxl j Calculate using the following formula:

[0116]

[0117] In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which data is obtained, m represents the total number of months for which data for the past m months is obtained, Q(j, k) represents the monthly output value of the j-th sub-industry in the k-th month, It represents the total output value of the j-th sub-industry for m months, and Rs(j,k) represents the number of employees in the j-th sub-industry in the k-th month.

[0118] The data analysis module further includes a first correlation unit and a second correlation unit, wherein the first correlation unit is used to convert the power efficiency Hyydxl of the j-th sub-industry into j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl jAfter dimensionless processing, the following correlation formula is used to generate the comprehensive index Zhzs of the j-th sub-industry: j :

[0119] Zhz j =γ1*Hyydxl j +γ2*Lsbl jfy +γ3*Rgxl j +A1

[0120] Where γ1, γ2 and γ3 represent the electricity efficiency of the j-th sub-industry, Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The weight value is adjusted and set by the user, 0<γ1<1, 0<γ2<1, 0<γ3<1, γ1+γ2+γ3=1, A1 represents the first correction constant value;

[0121] The second correlation unit generates the ratio of the electricity consumption efficiency of the high-end equipment manufacturing industry to the electricity consumption efficiency of the traditional equipment manufacturing industry through the following correlation formula: electricity consumption rate ratio Ydlb:

[0122]

[0123] Where Gdxl is the electricity consumption efficiency of high-end equipment manufacturing industry, and Ctxl is the electricity consumption efficiency of traditional equipment manufacturing industry.

[0124] In this embodiment, the data analysis module further includes a third calculation unit, a first association unit and a second association unit. The third calculation unit is used to calculate the labor efficiency (Rgxl) of a specific sub-industry (class j) according to the time series sub-industry data set. j ). By calculating the ratio of the total monthly output value of a specific sub-industry (class j) for m months to the total number of employees per month for m months in the specific sub-industry, the labor efficiency (Rgxl) of the specific sub-industry (class j) is obtained. j ), which reflects the monthly average labor efficiency of the sub-industry during the investigation period.

[0125] The first associated unit performs dimensionless processing (i.e., standardization or normalization) on electricity efficiency (Hyydxlj), green energy consumption ratio (Lsbljfy) and labor efficiency (Rgxlj) so that they can be compared and summed on the same scale to obtain the j-th specific sub-industry comprehensive index Zhzs j This formula integrates efficiency indicators from three different dimensions (electricity efficiency, green energy consumption ratio, and labor efficiency) into a comprehensive index, thereby comprehensively evaluating the overall performance of a specific sub-industry.

[0126] The second associated unit calculates the ratio of the electricity consumption efficiency of the high-end equipment manufacturing industry to that of the traditional equipment manufacturing industry to obtain the electricity consumption rate ratio Ydlb, which is used to reflect the degree of difference between the electricity consumption efficiency of the high-end equipment manufacturing industry and that of the traditional equipment manufacturing industry.

[0127] Example 7

[0128] See also Figure 1 , specifically, the evaluation module includes a first evaluation unit, a second evaluation unit and a third evaluation unit;

[0129] The first evaluation unit is used to compare and evaluate the ratio of the power consumption efficiency of the high-end equipment manufacturing industry to the power consumption efficiency of the traditional equipment manufacturing industry: the power consumption rate ratio Ydlb and the power consumption rate ratio threshold Q1, and obtain a first evaluation result, including:

[0130] If the electricity consumption ratio Ydlb>Q1, it means that the electricity consumption efficiency control of high-end equipment manufacturing industry is far ahead of that of traditional equipment manufacturing industry. It is worth learning from the advanced achievements of high-end equipment manufacturing industry to upgrade and transform traditional equipment manufacturing industry.

[0131] If 1<power consumption ratio Ydlb≤Q1, it means that the power consumption efficiency of high-end equipment manufacturing industry is ahead of that of traditional equipment manufacturing industry, and the power consumption efficiency control is not obvious. It is necessary to analyze the reasons, ensure R&D investment, and further upgrade and transform the high-end equipment manufacturing industry;

[0132] If the electricity consumption rate ratio Ydlb≤1, it means that the electricity consumption efficiency of the high-end equipment manufacturing industry is lower than that of the traditional equipment manufacturing industry. It is necessary to conduct on-site investigation, find out the reasons, replace advanced equipment, and further transform and upgrade the high-end equipment manufacturing industry.

[0133] The second evaluation unit is used to convert the j-th sub-industry comprehensive index Zhzs j Compare and evaluate with the comprehensive threshold Q2 to obtain a second evaluation result, including:

[0134] If the composite index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q2, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j <Comprehensive threshold Q2 indicates that the j-th sub-industry does not belong to the green, advanced and efficient industry, and sends the first early warning instruction to remind the j-th sub-industry that it needs to be transformed and upgraded. At the same time, the third evaluation unit is triggered through the j-th sub-industry electricity efficiency Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessment of the j-type sub-industry issues and obtain the third assessment results, including:

[0135] If the electricity efficiency of the j-th sub-industry is Hyydxl j ≥ power efficiency threshold Q3, indicating that the j-th sub-industry is highly efficient in power consumption and belongs to an advanced industry. If the power consumption efficiency of the j-th sub-industry is Hyydxl j <The power efficiency threshold Q3 indicates that the j-th sub-industry is inefficient in power consumption and belongs to a backward industry. The second warning instruction is issued and a strategy is generated: the power facilities of the j-th sub-industry are upgraded to ensure efficient power consumption;

[0136] If the consumption ratio of the fth green energy in the jth sub-industry is Lsbl jfy ≥ green energy threshold Q4, indicating that the j-th sub-industry belongs to the green environmental protection industry. If the consumption ratio of the f-th green energy in the j-th sub-industry is Lsbl jfy <Green energy threshold Q4, indicating that the j-th sub-industry relies on traditional fossil energy and does not belong to the green environmental protection industry, and the third warning instruction is issued, and the strategy is generated: upgrade and transform the j-th sub-industry to rely on green energy for production;

[0137] If the labor efficiency of the j-th sub-industry is Rgxl j ≥ labor efficiency threshold Q5, indicating that the j-th sub-industry has excellent automation and belongs to a high-efficiency industry. If the labor efficiency of the j-th sub-industry is Rgxl j <The labor efficiency threshold Q5 indicates that the automation level of the j-th sub-industry is unqualified and it is an inefficient industry. The fourth early warning instruction is issued and a strategy is generated: the automation level of the j-th sub-industry is upgraded to achieve reduction in staff and increase in efficiency.

[0138] In this embodiment, a modular system for industry evaluation and optimization is described, which is specifically divided into three evaluation units, aiming to judge the energy efficiency, environmental protection and automation level of different industries (especially sub-industries) through different indicators and thresholds, and propose corresponding transformation and upgrading strategies accordingly. The following is a detailed explanation:

[0139] The first assessment unit evaluates the energy efficiency performance of the high-end equipment manufacturing industry by comparing the electricity consumption rates of the high-end equipment manufacturing industry and the traditional equipment manufacturing industry, and accordingly puts forward corresponding improvement suggestions.

[0140] High-end equipment manufacturing industry usually shows higher electricity efficiency due to its strong technological innovation capability, extensive application of information technology and automation technology, as well as efficient energy management and energy-saving technology application. In contrast, traditional equipment manufacturing industry lags behind in technological innovation and energy-saving technology application, resulting in low electricity efficiency and more waste of resources.

[0141] Specifically, this evaluation process involves the following key steps and conclusions:

[0142] Evaluation logic and conclusion:

[0143] When the electricity consumption ratio Ydlb>Q1: This means that the high-end equipment manufacturing industry is far superior to the traditional equipment manufacturing industry in terms of electricity consumption control, which means that the high-end equipment manufacturing industry has achieved remarkable results in energy utilization and management. Its advanced achievements are worthy of reference by the traditional equipment manufacturing industry for upgrading and transformation to improve energy efficiency.

[0144] When 1<power consumption ratio Ydlb≤Q1, although the power consumption control of high-end equipment manufacturing industry is still better than that of traditional equipment manufacturing industry, this advantage is not obvious. This suggests that we need to further analyze the reasons. It may be that there is still room for improvement in some aspects of the high-end equipment manufacturing industry, or its advantages have not been fully utilized. Therefore, it is recommended to ensure R&D investment and further upgrade and transform the high-end equipment manufacturing industry to expand its advantages in power consumption control.

[0145] When the power consumption ratio Ydlb≤1, this is the most undesirable situation, indicating that the power consumption rate of the high-end equipment manufacturing industry is even lower than that of the traditional equipment manufacturing industry. This usually means that there are problems in energy utilization and management in the high-end equipment manufacturing industry, and immediate action is needed. It is recommended to conduct on-site investigations and thoroughly investigate the causes, which may be caused by equipment aging or poor management. In response to these problems, advanced equipment should be replaced and the high-end equipment manufacturing industry should be transformed and upgraded.

[0146] The second evaluation unit is used to preliminarily evaluate the comprehensive energy efficiency level of the j-th sub-industry, and judge whether it belongs to the green, advanced and efficient industry by comparing it with the comprehensive threshold Q2. Evaluation logic: If the comprehensive index of the j-th sub-industry is greater than or equal to Q2, it is judged as a green, advanced and efficient industry. If it is less than Q2, it is judged as a non-green, advanced and efficient industry, and the first early warning instruction is sent to indicate that the sub-industry needs to be transformed and upgraded. At the same time, the third evaluation unit is triggered for a more in-depth analysis.

[0147] After the second assessment unit determined that the industry was not green, advanced and efficient, the third assessment unit conducted a further in-depth assessment from three dimensions: electricity efficiency, green energy consumption ratio and labor efficiency.

[0148] Electricity efficiency (Hyydxlj): If it is higher than the electricity efficiency threshold Q3, it is considered to be efficient and belongs to an advanced industry; otherwise, it is considered to be inefficient and the electricity facilities need to be upgraded.

[0149] Green energy consumption ratio (Lsbljfy): If it is higher than the green energy threshold Q4, it is regarded as a green environmental protection industry; otherwise, it is regarded as relying on traditional fossil energy and needs to be upgraded to use green energy.

[0150] Labor efficiency (Rgxlj): If it is higher than the labor efficiency threshold Q5, it is considered to have an excellent degree of automation and belongs to a high-efficiency industry; otherwise, it is considered to have an insufficient degree of automation and requires automation upgrades.

[0151] The entire evaluation system uses hierarchical evaluation units, from comprehensive to specific, from preliminary to in-depth, to comprehensively evaluate the energy efficiency, environmental protection and automation levels of different sub-industries, and proposes targeted transformation and upgrading strategies based on this, which will help promote the development of related industries in the direction of green, efficient and automated, and achieve sustainable development.

[0152] Example 8

[0153] See also Figure 2 Specifically, a method for analyzing productivity based on power data includes the following steps:

[0154] Step 1: Industry data collection: Use data crawler technology to collect data through official websites and commercial data analysis websites, and extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources, and number of employees for five years according to sub-industry classification;

[0155] Step 2: Data processing: Clean and organize the collected data, remove duplicate, erroneous and invalid data, ensure the accuracy and completeness of the data, and use the processed data to construct a time series sub-industry data set;

[0156] Step 3: Data analysis: Use the pre-established time series analysis model to conduct in-depth analysis of power data and enterprise data to mine the correlation and trend information; calculate the power efficiency of the j-th sub-industry based on the time series sub-industry data set. j , obtain the electricity efficiency of high-end equipment manufacturing industry Gdxl, the electricity efficiency of traditional equipment manufacturing industry Ctxl, and the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j , the electricity consumption efficiency Gdxl of high-end equipment manufacturing industry and the electricity consumption efficiency Ctxl of traditional equipment manufacturing industry are correlated to generate the electricity consumption rate ratio Ydlb;

[0157] Step 4: Data evaluation: The first evaluation unit evaluates the ratio of electricity efficiency of high-end equipment manufacturing industry to that of traditional equipment manufacturing industry: electricity efficiency ratio Ydlb; the second evaluation unit evaluates the comprehensive index Zhzs of the jth sub-industry j The third evaluation unit is based on the electricity efficiency of the j-type sub-industry Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments on the j-th sub-industry issues and obtain corresponding assessment results and corresponding strategies;

[0158] Step 5: Trend Forecasting: Based on historical data and current trends, use machine learning and deep learning algorithms to forecast and assess future electricity demand and productivity development in each sub-sector;

[0159] Step 6. Organize the analysis and evaluation results into a report, put forward specific suggestions and improvement measures, and predict the future development trends of each sub-industry.

[0160] In this embodiment, a method for analyzing productivity based on power data is a systematic analytical framework that aims to evaluate and improve the productivity levels of different sub-sectors through power data analysis, especially in terms of energy utilization, technical efficiency and sustainable development. The following is a detailed explanation of each step:

[0161] Step 1: Industry data collection

[0162] Data source: Data is collected from multiple authoritative and professional websites (such as the State Grid, industry associations, and commercial data analysis websites) using data crawler technology.

[0163] Data content: Includes monthly electricity consumption, monthly output value, monthly consumption of various energy sources, and number of employees for each of the past five years, and is classified by sub-industry. These data provide the basis for subsequent in-depth analysis.

[0164] Step 2: Data processing

[0165] Data cleaning: Remove duplicate, erroneous and invalid data to ensure data accuracy and reliability.

[0166] Data organization: Organize the cleaned data into time series sub-industry data sets to prepare for subsequent analysis.

[0167] Step 3: Data Analysis

[0168] Model application: Use time series analysis models to conduct in-depth analysis of power data and enterprise data to reveal the correlation and trend between data.

[0169] Calculation of key indicators: Calculate key indicators such as electricity efficiency, green energy consumption ratio, labor efficiency, etc. of sub-industries, and generate a comprehensive sub-industry index to comprehensively evaluate the productivity level and sustainability of sub-industries.

[0170] Step 4: Data evaluation

[0171] Multi-level assessment:

[0172] The first evaluation unit: Evaluate the ratio of the electricity efficiency of high-end equipment manufacturing industry to that of traditional equipment manufacturing industry: the electricity efficiency ratio, and analyze the differences between the two in terms of technical level and energy utilization efficiency.

[0173] The second evaluation unit: evaluate the comprehensive index of sub-industries and make a preliminary judgment on the overall performance of sub-industries.

[0174] The third evaluation unit: Based on specific indicators such as electricity efficiency, green energy consumption ratio and labor efficiency, conduct a more in-depth evaluation of the sub-industry and propose corresponding improvement strategies.

[0175] Step 5: Trend Forecast

[0176] Forecasting Methodology: Use machine learning and deep learning algorithms, combined with historical data and current trends, to predict future electricity demand and productivity trends in each sub-sector.

[0177] Purpose of forecasting: To provide forward-looking decision-making support to enterprises and governments and help formulate long-term development plans.

[0178] Step 6: Report and Recommendations

[0179] Report compilation: The analysis and evaluation results are compiled into a report to clearly present the current status, problems, room for improvement and future development trends of each sub-industry.

[0180] Recommendations and measures: Based on the analysis results, specific recommendations and improvement measures are put forward to help enterprises improve productivity, optimize energy structure, improve energy efficiency, and promote sustainable development of the industry.

[0181] This approach provides strong support for improving the productivity level of various sub-industries through comprehensive and in-depth data analysis and evaluation, and helps promote the transformation, upgrading and sustainable development of the industry.

[0182] Example 9

[0183] See also Figure 3 Specifically, a device for analyzing productivity based on power data includes:

[0184] Processor: When executing instructions, the system and method are executed;

[0185] Memory: used to store computer instructions. When the processor executes the instructions, the above-mentioned system and method are executed;

[0186] A computer-readable storage medium: comprising a computer program or instructions, which, when executed on a computer, causes the computer to execute the above-mentioned system and method;

[0187] Specifically include:

[0188] Sub-industry data collection module: responsible for collecting monthly electricity consumption data, monthly output value, monthly consumption of various energy sources and number of employees by sub-industry classification;

[0189] Data processing module: responsible for data cleaning and sorting, and using the processed data to construct a time series sub-industry data set;

[0190] Data analysis module: performs computational analysis based on time series sub-industry data sets;

[0191] Evaluation module: Evaluate the green, advanced and efficient level of each sub-industry and provide rectification strategies; compare and evaluate the ratio of electricity efficiency of high-end equipment manufacturing industry and traditional equipment manufacturing industry: electricity efficiency ratio;

[0192] Forecasting module: Based on historical data and current trends, it uses machine learning and deep learning algorithms to predict and evaluate the future electricity demand and productivity development of each sub-industry.

[0193] In this embodiment, a device for analyzing productivity based on power data is described. The device integrates multiple key components and aims to improve the productivity level of each sub-industry through in-depth analysis of power data and evaluate its green, advanced and efficient level. The following is a detailed explanation of each component:

[0194] Processor: The processor is the core component of the device and is responsible for executing computer instructions stored in the memory. These instructions correspond to the above-mentioned systems and methods, that is, performing a series of operations such as power data analysis, processing, analysis, evaluation and prediction.

[0195] Memory: Memory is used to store computer instructions and data. When the processor needs to perform an operation, it reads the corresponding instructions from the memory and executes them. The instructions here correspond to the system and method for realizing the productivity of power data analysis, including steps such as data acquisition, processing, analysis, evaluation and prediction.

[0196] Computer readable storage medium: This is a physical medium, such as a hard disk, flash memory, etc., used to store computer programs or instructions. When these programs or instructions are run on a computer (or this device), they will instruct the computer to execute the above-mentioned systems and methods. This ensures the functionality and repeatability of the device.

[0197] Sub-industry data collection module: This module is responsible for collecting relevant data by sub-industry classification, including monthly electricity consumption data, monthly output value, monthly consumption of various energy sources and number of employees. These data are the basis for subsequent analysis and evaluation, and are crucial for understanding the operating status and energy usage of sub-industries.

[0198] Data processing module: The data processing module is responsible for cleaning and organizing the collected raw data. This includes removing duplicate, erroneous and invalid data to ensure the accuracy and completeness of the data. The processed data will be used to construct a time series sub-industry data set to provide a basis for subsequent in-depth analysis.

[0199] Data analysis module: Based on the time series sub-industry data set, the data analysis module performs various calculations and analysis tasks. This includes calculating key indicators such as the sub-industry's electricity efficiency, green energy consumption ratio, and labor efficiency, and generating evaluation results such as the sub-industry comprehensive index; these analysis results provide an important basis for subsequent evaluation and prediction.

[0200] Evaluation module: The evaluation module is responsible for evaluating the green, advanced and efficient level of each sub-industry and providing corresponding rectification strategies. It also compares and evaluates the ratio of electricity efficiency of high-end equipment manufacturing industry and traditional equipment manufacturing industry: electricity rate ratio, to reveal the differences in technology level and energy efficiency between high-end equipment manufacturing industry and traditional equipment manufacturing industry. These evaluation results help enterprises understand their position in the industry and formulate corresponding improvement plans.

[0201] Forecasting module: Based on historical data and current trends, the forecasting module uses machine learning and deep learning algorithms to predict and evaluate future power demand and productivity development in various sub-sectors. This helps companies and governments make forward-looking decision support to cope with future challenges and opportunities.

[0202] In summary, this device based on power data analysis productivity realizes the comprehensive collection, processing, analysis, evaluation and prediction of power data by integrating multiple key components. It provides strong data support for enterprises, helps to improve productivity, optimize energy structure, improve energy utilization efficiency, and promote the sustainable development of the industry.

[0203] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic, for example, the division of the modules is only one, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0204] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0205] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for analyzing productivity based on power data, characterized in that: include: Sub-industry data collection module: extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources and number of employees for five years according to sub-industry classification; Data processing module: cleans and organizes the collected data, removes duplicate, erroneous and invalid data, and uses the processed data to construct a time series sub-industry data set; Data analysis module: used to establish a time series analysis model, and calculate the power consumption per unit output value of the j-th sub-industry based on the time series sub-industry data set, that is, the power efficiency of the j-th sub-industry Hyydxl j ; Classify the sub-industries into high-end equipment manufacturing and traditional equipment manufacturing, calculate the electricity efficiency of high-end equipment manufacturing Gdxl and traditional equipment manufacturing Ctxl; calculate the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j : Evaluation module: If the comprehensive index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q1, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j < comprehensive threshold Q1, indicating that the j-th sub-industry does not belong to the green, advanced and efficient industry, sends the first warning instruction, and further calculates the power efficiency Hyydxl of the j-th sub-industry j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy , labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments of the j-th sub-industry issues, compare and analyze them with the corresponding thresholds, trigger corresponding warning instructions, and generate corresponding strategies; evaluate the ratio of electricity efficiency of high-end equipment manufacturing industry to that of traditional equipment manufacturing industry: electricity rate ratio, and analyze the differences in technology level and energy utilization efficiency between high-end equipment manufacturing industry and traditional equipment manufacturing industry; Prediction module: Use machine learning and deep learning algorithms to predict and evaluate the future electricity demand and productivity development of each sub-industry. Before conducting the prediction and evaluation, the collected and sorted historical data and current trend data of each sub-industry are input into the prediction module for training.

2. A system for analyzing productivity based on power data according to claim 1, characterized in that: The productivity mentioned includes: new generation information technology, biotechnology, new energy, new materials, high-end equipment, new energy vehicles, green environmental protection, civil aviation, ship and marine engineering equipment, artificial intelligence, quantum information, mobile communications, the Internet of Things and blockchain.

3. A system for analyzing productivity based on power data according to claim 1, characterized in that: For the same data x obtained from different channels, if the values ​​are different, the following formula is used for standardization: In the formula, i = 1, 2, 3, ..., n, i represents the sequence number of the same data obtained in the i-th channel, n represents the total number of the same data obtained in n different channels, x i represents the same data value captured on the i-th website, x max Indicates the maximum value of the same data obtained from n different channels, x min Indicates the minimum value of the same data obtained from n different channels.

4. The system for analyzing productivity based on power data according to claim 1, characterized in that: The data analysis module is used to establish a time series analysis model, including a first calculation unit, which is used to calculate and obtain the electricity efficiency Hyydxl of the j-th sub-industry based on the time series sub-industry data set: j , the electricity consumption efficiency of high-end equipment manufacturing industry Gdxl and the electricity consumption efficiency of traditional equipment manufacturing industry Ctxl; The electricity efficiency of the j-th sub-industry is Hyydxl j Calculate using the following formula: In the formula, j represents the sub-industry number, k = 1, 2, 3, ..., m, k represents the month number of the data, m represents the total number of months for which the data of the past m months are obtained, Q(j, k) represents the monthly electricity consumption of the j-th sub-industry in the k-th month, and P(j, k) represents the monthly output value of the j-th sub-industry in the k-th month; The electricity efficiency of the high-end equipment manufacturing industry Gdxl is calculated by the following formula: In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which the data is obtained, m represents the total number of months for which the data for the past m months is obtained, g = 1, 2, 3, ..., s, g represents the serial number of the high-end equipment manufacturing industry, s represents the total number of high-end equipment manufacturing industries, Q(g, k) represents the monthly electricity consumption of the g-th high-end equipment manufacturing industry in the k-th month, Q(g, k) represents the monthly output value of the g-th high-end equipment manufacturing industry in the k-th month, represents the total monthly electricity consumption of all s high-end equipment manufacturing industries in a total of m months. It represents the monthly output value of all s high-end equipment manufacturing industries in a total of m months; The electricity consumption efficiency Ctxl of the traditional equipment manufacturing industry is calculated by the following formula: In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for obtaining data, m represents the total number of months for obtaining data for the past m months, c = 1, 2, 3, ..., s, c represents the serial number of the traditional equipment manufacturing industry, q represents the total number of traditional equipment manufacturing industries, Q(c, k) represents the monthly electricity consumption of the cth traditional equipment manufacturing industry in the kth month, Q(c, k) represents the monthly output value of the cth traditional equipment manufacturing industry in the kth month, represents the total monthly electricity consumption of all q traditional equipment manufacturing industries in m months. It represents the monthly output value of all q traditional equipment manufacturing industries in a total of m months.

5. The system for analyzing productivity based on power data according to claim 1, characterized in that: The data analysis module also includes a second calculation unit, which is used to calculate and obtain: the consumption ratio Nybl of the yth energy in the jth sub-industry according to the time series sub-industry data set jy and the consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy , because the measurement units of various energy sources are different, according to the conversion coefficients of energy types issued by the energy management department, the consumption of various energy sources is first converted into the consumption of standard coal, and then the calculation is carried out; The consumption ratio of the yth energy source in the jth sub-industry is Nybl jy Calculate using the following formula: In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data of the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, N(j, k, y) represents the consumption of the yth type of energy in the kth month of the jth sub-industry, It represents the consumption of the yth type of energy in the jth sub-industry in m months. It represents the consumption of all t types of energy in the j-th sub-industry in m months; The consumption ratio of the fth green energy in the jth sub-industry Lsbl jfy Calculate using the following formula: Where, k = 1, 2, 3, ..., m, k represents the serial number of the month in which the data is obtained, m represents the total number of months in which the data for the past m months is obtained, j represents the serial number of the sub-industry, y = 1, 2, 3, ..., t, y represents the serial number of different types of energy, t represents the total number of energy types, f = 1, 2, 3, ..., u, f represents the serial number of different types of green energy, u represents the total number of green energy types, N(j, k, f) represents the f-th green energy consumption of the j-th sub-industry in the k-th month, N(j, k, y) represents the y-th energy consumption of the j-th sub-industry in the k-th month, represents the consumption of all u types of green energy in the j-th sub-industry in m months, It represents the consumption of all t types of energy in the j-th sub-industry within m months.

6. The system for analyzing productivity based on power data according to claim 1, characterized in that: The data analysis module also includes a third calculation unit, which is used to calculate and obtain the labor efficiency Rgxl of the j-th sub-industry based on the time series sub-industry data set. j , the labor efficiency of the j-th sub-industry is Rgxl j Calculate using the following formula: In the formula, k = 1, 2, 3, ..., m, k represents the serial number of the month for which data is obtained, m represents the total number of months for which data for the past m months is obtained, Q(j, k) represents the monthly output value of the j-th sub-industry in the k-th month, It represents the total output value of the j-th sub-industry for m months, and Rs(j,k) represents the number of employees in the j-th sub-industry in the k-th month.

7. The system for analyzing productivity based on power data according to claim 1, characterized in that: The data analysis module further includes a first correlation unit and a second correlation unit, wherein the first correlation unit is used to convert the power efficiency Hyydxl of the j-th sub-industry into j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j After dimensionless processing, the following correlation formula is used to generate the comprehensive index Zhzs of the j-th sub-industry: j : Yessss j =γ1*Hyydxl j +γ2*Lsbl jfy +γ3*Rgxl j +A1 Where γ1, γ2 and γ3 represent the electricity efficiency of the j-th sub-industry, Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The weight value is adjusted and set by the user, 0<γ1<1, 0<γ2<1, 0<γ3<1, γ1+γ2+γ3=1, A1 represents the first correction constant value; The second correlation unit generates the ratio of the electricity consumption efficiency of the high-end equipment manufacturing industry to the electricity consumption efficiency of the traditional equipment manufacturing industry through the following correlation formula: electricity consumption rate ratio Ydlb: Where Gdxl is the electricity consumption efficiency of high-end equipment manufacturing industry, and Ctxl is the electricity consumption efficiency of traditional equipment manufacturing industry.

8. The system for analyzing productivity based on power data according to claim 1, characterized in that: The evaluation module includes a first evaluation unit, a second evaluation unit and a third evaluation unit; The first evaluation unit is used to compare and evaluate the ratio of the power consumption efficiency of the high-end equipment manufacturing industry to the power consumption efficiency of the traditional equipment manufacturing industry: the power consumption rate ratio Ydlb and the power consumption rate ratio threshold Q1, and obtain a first evaluation result, including: If the electricity consumption ratio Ydlb>Q1, it means that the electricity consumption efficiency control of high-end equipment manufacturing industry is far ahead of that of traditional equipment manufacturing industry. It is worth learning from the advanced achievements of high-end equipment manufacturing industry to upgrade and transform traditional equipment manufacturing industry. If 1<power consumption ratio Ydlb≤Q1, it means that the power consumption efficiency of high-end equipment manufacturing industry is ahead of that of traditional equipment manufacturing industry, and the power consumption efficiency control is not obvious. It is necessary to analyze the reasons, ensure R&D investment, and further upgrade and transform the high-end equipment manufacturing industry; If the electricity consumption rate ratio Ydlb≤1, it means that the electricity consumption efficiency of the high-end equipment manufacturing industry is lower than that of the traditional equipment manufacturing industry. It is necessary to conduct on-site investigation, find out the reasons, replace advanced equipment, and further transform and upgrade the high-end equipment manufacturing industry. The second evaluation unit is used to convert the j-th sub-industry comprehensive index Zhzs j Compare and evaluate with the comprehensive threshold Q2 to obtain a second evaluation result, including: If the composite index of the j-th sub-industry is Zhzs j ≥ comprehensive threshold Q2, indicating that the j-th sub-industry belongs to the green, advanced and efficient industry; if the comprehensive index of the j-th sub-industry is Zhzs j <Comprehensive threshold Q2 indicates that the j-th sub-industry does not belong to the green, advanced and efficient industry, and sends the first early warning instruction to remind the j-th sub-industry that it needs to be transformed and upgraded. At the same time, the third evaluation unit is triggered through the j-th sub-industry electricity efficiency Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessment of the j-type sub-industry issues and obtain the third assessment results, including: If the electricity efficiency of the j-th sub-industry is Hyydxl j ≥ power efficiency threshold Q3, indicating that the j-th sub-industry is highly efficient in power consumption and belongs to an advanced industry. If the power consumption efficiency of the j-th sub-industry is Hyydxl j <The power efficiency threshold Q3 indicates that the j-th sub-industry is inefficient in power consumption and belongs to a backward industry. The second warning instruction is issued and a strategy is generated: the power facilities of the j-th sub-industry are upgraded to ensure efficient power consumption; If the consumption ratio of the fth green energy in the jth sub-industry is Lsbl jfy ≥ green energy threshold Q4, indicating that the j-th sub-industry belongs to the green environmental protection industry. If the consumption ratio of the f-th green energy in the j-th sub-industry is Lsbl jfy <Green energy threshold Q4, indicating that the j-th sub-industry relies on traditional fossil energy and does not belong to the green environmental protection industry, and the third warning instruction is issued, and the strategy is generated: upgrade and transform the j-th sub-industry to rely on green energy for production; If the labor efficiency of the j-th sub-industry is Rgxl j ≥ labor efficiency threshold Q5, indicating that the j-th sub-industry has excellent automation and belongs to a high-efficiency industry. If the labor efficiency of the j-th sub-industry is Rgxl j <The labor efficiency threshold Q5 indicates that the automation level of the j-th sub-industry is unqualified and it is an inefficient industry. The fourth early warning instruction is issued and a strategy is generated: the automation level of the j-th sub-industry is upgraded to achieve reduction in staff and increase in efficiency.

9. A method for analyzing productivity based on power data, applied to a system for analyzing productivity based on power data as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Industry data collection: Use data crawler technology to collect data through official websites and commercial data analysis websites, and extract monthly electricity consumption data, monthly output value, monthly consumption of various energy sources, and number of employees for five years according to sub-industry classification; Step 2: Data processing: Clean and organize the collected data, remove duplicate, erroneous and invalid data, ensure the accuracy and completeness of the data, and use the processed data to construct a time series sub-industry data set; Step 3: Data analysis: Use the pre-established time series analysis model to conduct in-depth analysis of power data and enterprise data to mine the correlation and trend information; calculate the power efficiency of the j-th sub-industry based on the time series sub-industry data set. j , obtain the electricity efficiency of high-end equipment manufacturing industry Gdxl, the electricity efficiency of traditional equipment manufacturing industry Ctxl, and the consumption ratio of the j-th sub-industry to the y-th energy Nybl jy , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j ; The electricity efficiency of the j-type sub-industry is Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j The j-th sub-industry comprehensive index Zhzs is generated by association j , the electricity consumption efficiency Gdxl of high-end equipment manufacturing industry and the electricity consumption efficiency Ctxl of traditional equipment manufacturing industry are correlated to generate the electricity consumption rate ratio Ydlb; Step 4: Data evaluation: The first evaluation unit evaluates the ratio of the electricity efficiency of the high-end equipment manufacturing industry to the electricity efficiency of the traditional equipment manufacturing industry: the electricity rate ratio Ydlb; The second evaluation unit's comprehensive index of the j-th sub-industry is Zhzs j The third evaluation unit is based on the electricity efficiency of the j-type sub-industry Hyydxl j , the consumption ratio of the fth type of green energy in the jth sub-industry Lsbl jfy and the labor efficiency of the j-th sub-industry Rgxl j Continue to conduct in-depth assessments on the j-th sub-industry issues and obtain corresponding assessment results and corresponding strategies; Step 5: Trend Forecasting: Based on historical data and current trends, use machine learning and deep learning algorithms to forecast and assess future electricity demand and productivity development in each sub-sector; Step 6. Organize the analysis and evaluation results into a report, put forward specific suggestions and improvement measures, and predict the future development trends of each sub-industry.

Images