Industrial power business index construction method, system and equipment based on multi-dimensional data indexes and medium

Abstract

The invention discloses an industrial power business index construction method, system and device based on a multi-dimensional data index and a medium, and relates to the technical field of industrial power analysis, and the method comprises the steps: obtaining a plurality of candidate indexes used for representing industrial business changes; determining an economic cycle reference date serving as an index comparison reference; performing preprocessing operation on the historical sequence of the candidate indexes; dividing the indexes into an advanced index, a consistent index and a lagging index; generating a preceding diffusion index, a consistent diffusion index and a lagging diffusion index; according to a preset weight determination rule, carrying out weighted summarization on various indexes to respectively obtain a preceding synthesis index, a consistent synthesis index and a lagging synthesis index; and various diffusion indexes and various synthesis indexes are used as a prosperity evaluation basis. According to the method, the diffusion index method and three indexes of synthesis leading, coincidence and lagging are comprehensively utilized, the economic cycle stage of the industry can be judged, the future trend can be deduced, and the problems of single model and insufficient accuracy in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of industrial power analysis technology, and in particular to a method, system, equipment and medium for constructing an industrial power prosperity index based on multidimensional data indicators. Background Technology

[0002] Electricity consumption serves as a "barometer" and "thermometer" of the national economy, and its changes are closely related to macroeconomic development, particularly the production and operation activities of various industries. Therefore, scientifically and accurately constructing an industrial electricity prosperity index is of paramount importance for real-time monitoring of industrial operations, predicting industrial electricity economic trends, and assisting government and enterprise decision-making.

[0003] In recent years, traditional methods have only studied the overall prosperity of the power sector, lacking adaptation to the characteristics of industrial sectors, and the explanatory power of general models is limited. Furthermore, the selection of power data for the early warning index pool has historically relied on a single dimension, failing to comprehensively reflect the connotation of industry prosperity and unable to distinguish whether electricity growth is driven by positive factors such as improved production efficiency and capacity expansion. In addition, coincident indices can be used to characterize the overall economic trajectory, determining the peaks and troughs of economic activity and benchmark trajectories, while lagging indices can analyze whether the current economic cycle has ended or serves the current cycle, playing a post-hoc verification role. Current patents only construct prosperity indices based on leading indicators, ignoring the fact that economic fluctuations are a gradual "diffusion" process within the macroeconomic system, and the analysis of important variables such as coincident and lagging indices, making it difficult to comprehensively characterize the industrial economy and power forecasting and early warning requirements under the background of high-quality development. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention provides a method, system, equipment and medium for constructing an industrial power prosperity index based on multi-dimensional data indicators.

[0005] Therefore, the problem that this invention aims to solve is that existing solutions neglect the fact that economic fluctuations are a process of gradual "diffusion" within the macroeconomic system, as well as the analysis of important variables such as coincidence indices and lagging indices, making it difficult to comprehensively depict the requirements for industrial economic and power forecasting and early warning under the background of high-quality development.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for constructing an industrial power prosperity index based on multidimensional data indicators, comprising: acquiring several candidate indicators for characterizing changes in industrial prosperity from multidimensional industrial power data according to preset indicator selection principles, forming a prosperity indicator pool; analyzing historical economic data to identify the peak and trough positions of the economic cycle and determining the economic cycle benchmark date as a reference for indicator comparison; performing preprocessing operations on the historical sequences of each indicator in the prosperity indicator pool to obtain standardized processed sequences for prosperity analysis; and determining the leading time of each indicator relative to the economic cycle benchmark date based on the temporal correlation between the benchmark indicator and other candidate indicators. The indicators are further divided into leading, coincident, and lagging indicators. The changing direction of each of the leading, coincident, and lagging indicator groups is identified. Based on the proportion of indicators in an expansionary state within each group, leading diffusion index, coincident diffusion index, and lagging diffusion index are generated. Based on the changing characteristics of each type of indicator, the indicators are weighted and aggregated according to a preset weighting rule, and combined with a long-term trend adjustment mechanism to obtain leading composite index, coincident composite index, and lagging composite index. The various diffusion indices and composite indices are used as the basis for economic climate evaluation to form an industrial power prosperity index that characterizes the stage, operating trend, and degree of change in the industrial economic cycle.

[0007] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators according to the present invention, the step of obtaining several candidate indicators for characterizing changes in industrial prosperity includes: determining the overall data range from multidimensional data as the source of candidate indicators based on the structural characteristics of industrial economic operation; within the overall data range, comprehensively evaluating and screening various data items according to preset indicator selection principles to form a set of candidate indicators; conducting prosperity response characteristic analysis on the set of candidate indicators to examine the performance patterns of each data item in the historical prosperity change process, and finally determining the candidate indicators used to construct the prosperity indicator pool based on the ability to characterize changes in industrial prosperity.

[0008] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in this invention, the step of determining the economic cycle benchmark date as a reference for indicator comparison includes: selecting a set of economic indicators that reflect economic fluctuations and are consistent with economic cycle fluctuations; initially determining the benchmark date for economic fluctuations based on the economic indicators; comparing the benchmark date with the business cycle chronology; and finally selecting the economic cycle benchmark date.

[0009] The beneficial effects of this preferred technical solution are as follows: by accurately determining the base date of the economic cycle, the classification of leading, consistent, and lagging indicators can have a unified time base, improving the rationality and systematicness of indicator classification, thereby enhancing the rigor of the overall economic climate index construction process.

[0010] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in this invention, the preprocessing operation of the historical sequences of each indicator in the prosperity indicator pool includes: performing a consistency check on the historical sequences of each indicator in the prosperity indicator pool, identifying missing data, and completing the missing values ​​using a preset imputation strategy; normalizing the completed historical sequences; performing seasonal decomposition on the normalized historical sequences; and performing trend decomposition on the seasonally decomposed historical sequences.

[0011] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in this invention, the step of classifying the indicators into leading indicators, consistent indicators, and lagging indicators includes: comparing the historical change sequences of each candidate indicator in the prosperity indicator pool with those of the benchmark indicator to observe the relative change patterns in the time direction and preliminarily judging the time response characteristics of the candidate indicators; based on the preliminary judgment, by identifying the response order of the candidate indicators to the trend changes of the benchmark indicator in different time periods, judging whether the trend is reflected before the change in economic activity, or whether it changes synchronously with the benchmark indicator, or whether it shows a corresponding trend after the change in the benchmark indicator; combining the patterns of the candidate indicators in terms of time response direction, change rhythm, and the location of characteristic nodes, indicators that show trend changes before the turning point of the benchmark indicator are classified as leading indicators; indicators that show synchronous fluctuation patterns with the benchmark indicator at change nodes are classified as consistent indicators; and indicators that lag behind the benchmark indicator in showing trend changes are classified as lagging indicators.

[0012] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators according to the present invention, the generation of the leading diffusion index, the uniform diffusion index, and the lagging diffusion index includes: statistically analyzing the number of indicators in the leading indicator group, the uniform indicator group, and the lagging indicator group that are in an expansion state at the same point in time; obtaining expansion ratio information by comparing the ratio of the expansion state to the total number of indicators in the group; and using the statistically obtained expansion ratio information as the basis for characterizing the diffusion state to form the leading diffusion index, the uniform diffusion index, and the lagging diffusion index, respectively.

[0013] As a preferred embodiment of the method for constructing an industrial power prosperity index based on multidimensional data indicators according to the present invention, the steps of obtaining the leading composite index, the coincident composite index, and the lagging composite index respectively include: extracting change features from the leading indicator group, the coincident indicator group, and the lagging indicator group to form a standardized change expression; based on the standardized change expression, weighting each indicator in the leading indicator group, the coincident indicator group, and the lagging indicator group according to a preset weight determination rule; and performing a trend adjustment operation on the weighted result based on the trend of the economic cycle to form the leading composite index, the coincident composite index, and the lagging composite index respectively.

[0014] The beneficial effects of this preferred technical solution are as follows: by standardizing and weighting the indicators within the group, the overall trend of each group of indicators can be comprehensively analyzed, so that the occasional fluctuations of a single indicator will not have an excessive impact on the results, thereby improving the robustness of the composite index.

[0015] To address the aforementioned technical problems, this invention provides the following technical solution: a system for constructing an industrial power prosperity index based on multidimensional data indicators, comprising: an indicator pool generation module, a data processing module, an indicator classification module, and an index generation module; the indicator pool generation module obtains several candidate indicators for characterizing changes in industrial prosperity from multidimensional industrial power data according to preset indicator selection principles, forming a prosperity indicator pool; the data processing module analyzes historical economic data, identifies the peak and trough positions of economic cycles, determines the economic cycle benchmark date as a reference for indicator comparison, and performs preprocessing operations on the historical sequences of each indicator in the prosperity indicator pool to obtain standardized processed sequences for prosperity analysis; the indicator classification module classifies indicators based on the time series between the benchmark indicator and other candidate indicators. The correlation is used to determine the leading degree of each indicator relative to the base date of the economic cycle, and then the indicators are divided into leading indicators, coincident indicators, and lagging indicators. The index generation module identifies the changing direction of the leading indicator group, coincident indicator group, and lagging indicator group respectively. Based on the proportion of indicators in the expansion state in each group, the leading diffusion index, coincident diffusion index, and lagging diffusion index are generated. Based on the changing characteristics of various indicators, the indicators are weighted and summarized according to the preset weight determination rules, and combined with the long-term trend adjustment mechanism, the leading composite index, coincident composite index, and lagging composite index are obtained respectively. The various diffusion indices and various composite indices are used as the basis for economic climate evaluation to form an industrial power prosperity index that represents the stage, operation trend, and changes in the degree of prosperity of the industrial economic cycle.

[0016] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described above.

[0017] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described above.

[0018] The beneficial effects of this invention are as follows: a specialized industrial prosperity index is constructed, which solves the problem of insufficient explanatory power caused by the lack of specificity in existing general models, thereby improving the accuracy and applicability of industrial prosperity assessment.

[0019] In terms of the construction method of the industrial power prosperity index, the diffusion index method and three types of composite leading, consistent and lagging indicators are comprehensively used. It can not only determine the stage of the economic cycle in which the industry is located, but also infer future trends, identify the degree of warning, and help determine the peak and trough of economic activities, thereby verifying the current cycle status and the integrity of historical cycles, and solving the problems of previous models being too simple and lacking accuracy.

[0020] Compared with existing power prosperity index methods, the industrial power prosperity index construction method proposed in this invention constructs diffusion index and composite index through a multi-dimensional data indicator pool, which has good adaptability, timeliness, and comprehensive and accurate early warning. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for constructing an industrial power prosperity index based on multidimensional data indicators, as described in Example 1.

[0023] Figure 2 This is a graph showing the industrial diffusion index synthesis results of an industrial power prosperity index construction method based on multidimensional data indicators in Example 3.

[0024] Figure 3 This is a graph showing the synthesis results of the leading index and the coincident index in the industrial expanded composite index of the industrial power prosperity index construction method based on multidimensional data indicators in Example 3.

[0025] Figure 4 This is a graph showing the composite results of the coincident index and the lag index in the industrial expanded composite index of the industrial power prosperity index construction method based on multidimensional data indicators in Example 3. Detailed Implementation

[0026] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0027] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0028] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for constructing an industrial power prosperity index based on multidimensional data indicators, including: S1: From the multidimensional data of industrial power, according to the preset indicator selection principles, obtain several candidate indicators to characterize changes in industrial prosperity, and form a prosperity indicator pool.

[0029] S2: Analyze historical economic data to identify the peak and trough positions of the economic cycle and determine the benchmark date of the economic cycle as a reference for indicator comparison.

[0030] S3: Perform preprocessing operations on the historical sequences of each indicator in the economic indicator pool to obtain standardized processed sequences for economic analysis.

[0031] S4: Based on the time-series correlation between the benchmark indicator and other candidate indicators, determine the leading degree of each indicator relative to the benchmark date of the economic cycle, and then classify the indicators into leading indicators, congruent indicators and lagging indicators.

[0032] S5: Identify the changing directions of the leading indicator group, the consistent indicator group, and the lagging indicator group respectively, and generate the leading diffusion index, the consistent diffusion index, and the lagging diffusion index based on the proportion of indicators in the expansion state within each group.

[0033] S6: Based on the changing characteristics of various indicators, the indicators are weighted and aggregated according to the preset weight determination rules, and combined with the long-term trend adjustment mechanism, the leading composite index, the consistent composite index and the lagging composite index are obtained respectively.

[0034] S7: Using various diffusion indices and composite indices as the basis for economic climate evaluation, an industrial power climate index is formed to characterize the stages, operating trends, and changes in the degree of prosperity of the industrial economic cycle.

[0035] It should be noted that some existing patents and research focus on leading indicator systems, but these have significant drawbacks: relying solely on leading indicators can easily lead to one-sided judgments on economic conditions; consistent indicators can more accurately reflect the current stage, but they are often overlooked; lagging indicators can be used to verify the integrity of the cycle, but they are also often missing, making it difficult for the economic index to form a comprehensive capability of prediction (leading), judgment of the current situation (synchronous), and verification of the cycle (lagging).

[0036] Therefore, in response to the above problems, such as Figure 1 As shown, through steps S1-S7, an initial set of indicators is first established based on the core information sources of industrial activities. Then, representative cyclical turning points are identified by combining the economic operation trajectory, serving as the time benchmark for subsequent indicator classification and index calculation. Subsequently, the historical sequences of each indicator are supplemented, adjusted, and standardized to make data from different dimensions and sources comparable. Based on this, the temporal response sequence and change patterns of each indicator are analyzed, thereby classifying them into leading, synchronous, or lagging types. For each type of indicator, the direction of expansion or contraction is further identified, and diffusion information that can characterize the consistent behavior of the indicator group is aggregated. Through comprehensive processing of the indicator change magnitude, weight allocation, and trend structure, three types of synthetic indices reflecting the characteristics of economic climate change are generated. Finally, this invention organically integrates the above indices to construct an industrial power climate index system that can be used to identify economic cycle stages, judge operating trends, and support forecasting and early warning.

[0037] Example 2, refer to Figure 2 This is the second embodiment of the present invention, which differs from the first embodiment in that: a method for constructing an industrial power prosperity index based on multidimensional data indicators further includes, in step S1, obtaining several candidate indicators for characterizing changes in industrial prosperity, including the following steps A1-A3: A1: Based on the structural characteristics of industrial economic operation, determine the overall data range from multidimensional data as the source of candidate indicators.

[0038] A2: Within the overall data scope, based on the preset indicator selection principles, a comprehensive evaluation and screening of various data items is conducted to form a set of candidate indicators.

[0039] A3: Conduct economic response characteristic analysis on the candidate indicator set, examine the performance patterns of each data item in the historical economic change process, and finally determine the candidate indicators used to construct the economic indicator pool based on the ability to represent changes in industrial economic conditions.

[0040] In this embodiment of the application, step A2 adopts an indicator selection method based on the principle of economic representativeness, including the following steps A211-A213: A211: Analyze multidimensional data to identify the main driving factors that reflect the state of industrial operation, the level of industrial prosperity, and macroeconomic fluctuations, determine the key economic elements that have a direct or indirect impact on changes in industrial prosperity, and focus on data items related to these elements.

[0041] A212: Based on the identified key influencing factors, a comprehensive judgment is made on the economic meaning, industry indicative ability, industry coverage, and explanatory ability of candidate data items to reflect changes in the economic cycle. Data items that can accurately reflect the core changing trends of economic activities are selected first, while data items with weak economic indicative ability or too narrow explanatory scope are eliminated.

[0042] A213: Combining economic theory logic and industrial operation rules, data items with high economic representativeness after evaluation are summarized and organized to form a set of candidate indicators that better reflect the internal mechanism of economic fluctuations, which will serve as the basis for constructing the industrial prosperity indicator pool.

[0043] In an optional implementation, the indicator selection principle can also adopt an indicator screening method based on statistical quality principles, including the following steps A221-A223: A221: Examine the historical sequence of each candidate data item in the multidimensional data to confirm that it has a sufficiently long statistical period, relatively complete historical data records and high continuity, and exclude data items with a large number of missing values, significant gaps or excessively long statistical intervals.

[0044] A222: The statistical quality of data items is evaluated based on the credibility of the data source, the consistency of statistical standards, the stability of historical release rules, and abnormal fluctuations. Data items with reasonable numerical fluctuations, stable statistical standards, and authoritative sources are prioritized for retention, while data items with insufficient statistical quality or significant external noise are removed.

[0045] A223: After evaluation, data items that meet the requirements of statistical continuity, stability and reliability will be summarized to form a set of candidate indicators with a good statistical foundation, so as to ensure the data credibility and stability in the subsequent construction of the business climate index.

[0046] In another alternative implementation, the indicator selection principle can also adopt an indicator screening method based on the principle of timeliness, including the following steps A231-A233: A231: For candidate data items in multidimensional data, analyze their release frequency, update interval and reporting cycle, give priority to data items that can be published regularly on a monthly or quarterly basis, and eliminate data with too long a release cycle or unstable updates.

[0047] A232: In combination with the rhythmic characteristics of industrial economic changes, assess the responsiveness of data items to fluctuations in the industrial economy, select data items that can promptly reflect the direction of change, cycle nodes and trend reversals during economic changes, and exclude data items that have significant lag or cannot promptly reflect economic changes.

[0048] A233: Data items with stable release cycles, timely updates, and high responsiveness to economic conditions will be summarized to form a set of candidate indicators with timeliness advantages, which will be used to improve the timeliness of economic index monitoring and early warning.

[0049] It should be noted that this step, by selecting representative indicators from multidimensional comprehensive data, can avoid one-sided indicator selection and make the selected candidate indicators have a more complete economic meaning, thereby improving the explanatory power of the industrial prosperity index for actual economic operation. Through the preset indicator selection principles, data items with inconsistent data caliber, unstable release frequency, or incomplete historical records can be effectively filtered to ensure that subsequent calculations are based on a stable and reliable data foundation.

[0050] Furthermore, in step A2, determining the economic cycle benchmark date for indicator comparison includes the following steps B1-B2: B1: Select a set of economic indicators that reflect economic fluctuations and are consistent with economic cycle fluctuations, and preliminarily determine the base date of economic fluctuations based on the economic indicators.

[0051] B2: By comparing the reference economic cycle timeline with the initially determined base date, the final economic cycle base date is selected.

[0052] In this embodiment of the application, step B1, which initially determines the base date for economic fluctuations, adopts a base date determination method based on diffusion index feature identification, including the following steps B111-B113: B111: From a variety of indicators that can characterize changes in macroeconomic operations, select several representative data items that can reflect the trend of economic expansion or contraction to form a set of indicators for identifying the characteristics of economic fluctuations, and construct a multi-indicator diffusion analysis system based on this.

[0053] B112: By comparing the trend changes of the indicator set over historical periods, identifying the expansion and contraction quantities at each point in time, and obtaining a diffusion characteristic sequence reflecting the overall degree of economic expansion, we can make a preliminary judgment on where a consistent upward or downward trend will occur.

[0054] B113: Analyze the time intervals in the diffusion sequence where there are large-scale synchronous rises or falls, regard such positions as possible economic cycle peaks or troughs, and take the time nodes with the most significant changes as candidate economic cycle benchmark dates.

[0055] In an optional implementation, the baseline date for initially determining economic fluctuations can also be determined using a baseline date determination method based on trend inflection point identification, including the following steps B121-B123: B121: Extract long-term trend components from multiple key indicators reflecting macroeconomic activities, and obtain a trend sequence that can represent the overall direction of economic operation through smoothing, trend extraction, or structural change identification.

[0056] B122: Analyze the slope changes, inflection point positions, and trend reversal intervals of trend sequences to determine in which time periods the trend changes from continuous rise to fall, or from fall to rise, thereby identifying potential turning points representing the peaks or troughs of the economic cycle.

[0057] B123: The identified trend inflection points are comprehensively judged based on the magnitude of the reversal, the speed of change, and the duration, and the points with the most significant reversal characteristics are selected as the candidate set of preliminary benchmark dates for the economic cycle.

[0058] In another alternative implementation, the baseline date for initially determining economic fluctuations can also be determined using a baseline date determination method based on statistical change point detection, including the following steps B131-B133: B131: Integrating multiple economic indicators in a certain way to form a comprehensive sequence that can be used to detect changes in statistical structure, so that the sequence can stably reflect the overall operating status of the macroeconomy and its changing trends.

[0059] B132: Perform statistical change point detection on the composite sequence to identify the locations where the mean, variance, or structural patterns of the sequence change significantly over a historical period, and regard these change points as potential turning points of economic fluctuations.

[0060] B133: Detected statistical change points are filtered according to significance, direction of change, and persistence, and the points that correspond to the phased changes in economic operation are selected as candidate positions for the preliminary base date of the economic cycle.

[0061] It should be noted that by analyzing the common change patterns of multiple macroeconomic indicators, the bias caused by the fluctuation of a single indicator can be reduced, and the accuracy of identifying historical peaks and troughs can be improved. By combining the business cycle chronology with records of macroeconomic phenomena, the initially identified cycle turning points can be cross-validated to ensure that the base date has stable economic logic support, rather than accidental fluctuations caused by short-term disturbances.

[0062] Furthermore, in step S3, the preprocessing operation performed on the historical series of each indicator in the economic indicator pool includes the following steps C1-C4: C1: Perform a consistency check on the historical series of each indicator in the economic indicator pool, identify any missing data, and fill in the missing values ​​using a preset imputation strategy.

[0063] C2: Normalize the completed historical sequence.

[0064] C3: Perform seasonal decomposition on the normalized historical sequence.

[0065] C4: Perform trend decomposition on the historical series after seasonal decomposition.

[0066] In this embodiment of the application, step C1 employs an interpolation strategy based on time trend inference, including the following steps C111-C113: C111: Perform overall trend analysis on indicator sequences with missing records, identify their rising, falling, or cyclical fluctuation characteristics over a long period of time, and generate a trend reference sequence that can represent the development direction of the indicator, providing a stable benchmark for subsequent completion.

[0067] C112: Based on the time position of the missing point in the sequence, map it to the trend reference sequence, analyze the positional characteristics of the interval in the trend structure, including the slope of the trend, the direction of change, and the strength of the trend, so as to determine the trend pattern that the missing point should follow.

[0068] C113: By combining the changing patterns of the trend reference sequence, the values ​​of missing points are inferred. By ensuring that the interpolation results are consistent with the overall trend, the completed sequence is guaranteed to be continuous, smooth, and does not deviate from the long-term change trajectory of the original indicator in the global trend.

[0069] In an optional implementation, the interpolation strategy may also employ an interpolation strategy based on adjacent association features, including the following steps C121-C123: C121: Organize the valid values ​​before and after the missing position, identify the variation range, fluctuation pattern and slope characteristics within the local range, so as to obtain structural information that can reflect the local behavior of the segment.

[0070] C122: Based on local structural characteristics, determine whether the missing point is in a stable segment, a transition segment, or a fluctuating segment, and analyze the coherence between the data before and after it to determine the transition method and local structural matching strategy to be used during completion.

[0071] C123: Based on the changing trend of data before and after in the neighborhood, the missing points are imputed by constructing a smooth transition or maintaining local consistency, so that the imputed values ​​are naturally connected in the local range, ensuring that there is no break in the local trend or unreasonable jump.

[0072] In another alternative implementation, the interpolation strategy may also employ a multi-index correlation-based interpolation strategy, including the following steps C131-C133: C131: Conduct correlation analysis on other indicators in the economic indicator pool, and select auxiliary indicators that are strongly correlated with the missing indicators in terms of trend direction, cycle characteristics, or fluctuation structure as reference information sources for imputation.

[0073] C132: Analyze the changes of the selected auxiliary indicators during the missing time period to identify their current trend direction, change magnitude and fluctuation strength, in order to establish a synchronous or lagging relationship with the missing indicators.

[0074] C133: Based on the changing characteristics of auxiliary indicators in the missing interval, and combined with the historical correlation pattern between the two, the missing position of the target indicator is inferred and filled in, so that the filling result can be consistent with the relevant indicators in terms of the direction of change and fluctuation structure, thereby ensuring that the filled sequence has reasonable economic logic.

[0075] To further explain, step C2, the normalization process for the completed historical sequence, specifically includes converting all data into numerical representations between 60 and 100: Among them, positive: ; In reverse: ; in, To obtain time series data for the indicator pool, This is the smallest time series data in the indicator pool. This is the largest time series data in the indicator pool.

[0076] Where the median is: Judgment condition: ; yes: ; no: ; in, The values ​​are obtained from the time series data in the indicator pool. This is a dataset for the indicator pool.

[0077] In step C3, seasonal decomposition is performed using X-12-ARIMA for seasonal adjustment. X-12-ARIMA is a statistical method developed by the U.S. Census Bureau for estimating and removing seasonal components from economic time series data.

[0078] In step C4, the trend decomposition uses the Baxter-King (BK) filter to divide the time series into trend, periodic and noise components, which can eliminate many of the noise-like behaviors shown above; the full name of BK filter is Baxter-King filter, and its core purpose is to decompose an economic time series into trend components and periodic components.

[0079] It should be noted that by filling in missing data, the originally discontinuous indicator series due to gaps or omissions is restored to a complete and calculable series, avoiding deviations or unprocessable situations in the calculation of the business climate index; normalization processing can unify data from different sources, with different dimensions and different fluctuation amplitudes to the same scale, ensuring that the subsequent calculation of diffusion index and composite index is not affected by differences in magnitude; seasonal decomposition and trend decomposition can eliminate periodic noise and seasonal interference, making the final indicator series used for calculation more reflective of the true trend of economic activity, thereby improving the accuracy of the business climate index in reflecting economic changes.

[0080] Furthermore, in step S4, classifying the indicators into leading indicators, consistent indicators, and lagging indicators includes the following steps D1-D3: D1: Compare the historical change sequences of each candidate indicator in the economic indicator pool with the benchmark indicator to observe the relative change patterns in the time direction and make a preliminary judgment on the time response characteristics of the candidate indicators.

[0081] D2: Based on the initial judgment, by identifying the response order of candidate indicators to the trend changes of benchmark indicators in different time periods, it is determined whether the trend is reflected before the change in economic activity, whether it changes synchronously with the benchmark indicator, or whether the corresponding trend is shown after the change in the benchmark indicator.

[0082] D3: Based on the patterns of candidate indicators in terms of time response direction, change rhythm, and the location of characteristic nodes, indicators that show trend changes before the turning point of the benchmark indicator are classified as leading indicators; indicators that show synchronous fluctuation patterns with the benchmark indicator at change nodes are classified as consistent indicators; and indicators that lag behind the benchmark indicator in showing trend changes are classified as lagging indicators.

[0083] Specifically, let's set As a benchmark, As the selected indicator, The time zone correlation coefficient is given by the formula: in, The number of benchmark indicators This represents the number of periods ahead or behind; a negative value indicates ahead, and a positive value indicates behind. for The time difference correlation coefficient of the period, The number of data points after all data has been collected. The average value of the selected indicators. This is the average value of the benchmark indicator. When selecting economic indicators, the selected indicators are generally calculated to determine the time-varying correlation coefficients at different lag periods, and the highest time-varying correlation coefficient is selected as: in, This represents the maximum delay.

[0084] This largest time difference correlation coefficient reflects the time difference correlation between the selected indicator and the benchmark indicator, and the corresponding delay number This indicates the leading or lagging period. (This model...) Values ​​≤-3 are calculated as the leading period and represented as leading indicators. ≥3 indicates a lag period, representing a lagged indicator; -3 < <3 indicates a period of consistency, which is considered a consistent indicator. When classifying the selected economic indicators, the following should be noted: 1) The correlation coefficient of each indicator should generally be greater than 0.5; 2) The magnitude of the correlation coefficient is not limited by the sign.

[0085] Furthermore, in step S5, generating the leading diffusion index, the uniform diffusion index, and the lagging diffusion index includes the following steps E1-E2: E1: Statistically count the number of indicators in the leading indicator group, the consistent indicator group, and the lagging indicator group that are in an expansion state at the same point in time. Obtain the expansion ratio information by comparing the ratio of the expansion state to the total number of indicators in the group.

[0086] E2: Using the statistically obtained expansion ratio information as the basis for characterizing the diffusion state, three diffusion indices are formed: the leading diffusion index, the coincident diffusion index, and the lagging diffusion index. The leading diffusion index reflects the forward-looking signal of the overall leading indicators on the upward or downward trend of the economy, the coincident diffusion index reflects the degree of synchronous change of the overall economic activity, and the lagging diffusion index reflects the following performance of economic changes on lagging indicators. Thus, three types of diffusion indices are formed to describe the structural characteristics of economic changes.

[0087] Specifically, the so-called diffusion index For the first (leading, consistent, or lagging) indicator group The ratio of the number of monthly expansion (increase) indicators to the total number of indicators used in the group is expressed as: in, As a leading indicator group, For a consistent indicator group, For lagging indicator groups, For the first Month Group expansion index number The indicator used is [number]. To determine whether an expansion is comparable to a specific point in time, it is generally ideal to compare the current month's value with the previous month's value. However, this can be subject to deviations due to rule changes. Therefore, to avoid such deviations, a comparison interval of 3 months is considered.

[0088] Furthermore, in step S6, obtaining the leading synthesis index, the coincident synthesis index, and the lagging synthesis index respectively includes the following steps F1-F3: F1: Extract change features from leading indicator groups, consistent indicator groups, and lagging indicator groups to form standardized change expressions.

[0089] F2: Based on standardized change expressions, each indicator in the leading indicator group, the consistent indicator group, and the lagging indicator group is weighted according to a preset weight determination rule.

[0090] F3: Based on the trend of the economic cycle, a trend adjustment operation is performed on the weighted result to form the leading composite index, the coincident composite index, and the lagging composite index respectively.

[0091] Specifically, to find the symmetrical rate of change of a single indicator, let the month-on-month growth rate sequence of the original indicator be... ,in Given the number of indicators, first calculate their symmetrical rate of change. Represented as: when Then: in, For the first Individual indicators The symmetrical rate of change at time t, expressed as a percentage.

[0092] Calculate the standardization rate : Indicates the first The standardized variation factor of each indicator, where N represents the number of standardized periods, then use Will Standardization yields the standardized average rate of change. Represented as: Then, the average rate of change of the leading, consistent, and lagging indicators are calculated respectively. Represented as: in, The number of indicators within the same category. It is the first The weight of the indicator.

[0093] For each Divide by between-group standardized factor Then we obtain the standardized average rate of change. in, It is a consistent indicator group .

[0094] Find the initial composite index For various indicators =100, and: Seeking trend adjustment in, It is the average of the first cycle. It is the average of the last cycle. This represents the number of periods between the first and last cycle centers. The average trend of each indicator calculated using the above method is called the average trend of the consensus indicator, denoted as [value missing]. .

[0095] Find the composite index in, for Divide by the average of the base year.

[0096] In this embodiment of the application, in step F2, the weight determination rule adopts a weight determination method based on the representativeness of the index, including the following steps F211-F213: F211: For each indicator in the leading, congruent, and lagging indicator groups, a comprehensive assessment is conducted based on its economic meaning, industry coverage, and typicality of the economic activities in this category to identify key indicators that can more fully characterize the core features of this type of economic change.

[0097] F212: Based on the results of the representativeness assessment of each indicator, higher weights are given to indicators with stronger core characteristics, and lower weights are given to indicators with relatively weak economic explanatory power or narrow representative scope, so that the weighted results can more accurately reflect the main direction of change of this type of indicator.

[0098] F213: Fix the weight allocation results obtained from the representative analysis as the weight system of this type of indicator, and perform the aggregation according to this system in the subsequent weighted calculation so that the final composite index can highlight the part of this type of indicator that is most indicative of changes in economic prosperity.

[0099] In an optional implementation, the weight determination rule may also employ a weight determination method based on index stability, including the following steps F221-F223: F221: Perform volatility, stability, and structural continuity analysis on the historical series of various indicators to identify which indicators exhibit less volatility, higher consistency, and more stable data characteristics in long-term performance.

[0100] F222: Assign higher weights to data items that are more stable, less volatile, and more consistent over time, and set lower weights to data items that are less stable, more volatile, or more susceptible to external factors, so that the weighted result can more stably reflect the overall trend of this type of indicator.

[0101] F223: Construct a corresponding weighting system based on the results of stability analysis. This system can improve the stability of the composite index during weighted aggregation, reduce the impact of abnormal fluctuations on the final index, and thus obtain a smoother composite index with long-term indicative significance.

[0102] In another alternative implementation, the weight determination rule can also employ a weight determination method based on index sensitivity, including the following steps F231-F233: F231: Analyze the response of various indicators in different economic phases to identify which indicators have a faster or more obvious response to economic upturns, downturns or fluctuations, thereby determining their sensitivity in reflecting changes in economic conditions.

[0103] F232: Higher weights are given to indicators that react quickly to changes in the economic cycle, show obvious trend turning points, or have high recognizability, while lower weights are given to indicators that react slowly, have weak changes, or are not sensitive enough to changes in the economy, so that the weighted aggregation can better highlight the key characteristics of changes in the economy.

[0104] F233: Based on the sensitivity assessment results, a corresponding weighting system is established, and comprehensive calculations are performed according to this system in the subsequent weighting process, so that the final composite index has a stronger ability to identify cycles and divide stages, and can reflect the direction and speed of economic changes in a timely manner.

[0105] It should be noted that this step, by standardizing and weighting the indicators within the group, can comprehensively analyze the overall trend of each group of indicators, ensuring that occasional fluctuations of a single indicator do not have an excessive impact on the results, thus improving the robustness of the composite index. The preset weight determination rules can allocate weights based on different factors such as representativeness, stability, and sensitivity, making the composite index more prominent indices that are most indicative of economic prosperity, thereby improving the economic rationality and explanatory power of the index.

[0106] Example 3 is the third embodiment of the present invention. It differs from the previous two embodiments in that, in order to verify and illustrate the technical effects used in this method, this embodiment uses actual experimental results to verify the real effects of this method.

[0107] The following example, using the construction process and practical application of an industrial power prosperity index in a certain province, further illustrates the present invention.

[0108] Based on the selection principles of benchmark indicators and the benchmark date for economic cycle fluctuations, 20 monthly economic and electricity indicators were selected from 2011 to 2023, including industrial electricity consumption, electricity consumption in ferrous metal smelting and rolling processing, electricity consumption in non-ferrous metal smelting and rolling processing, electricity consumption in non-metallic mineral products industry, average utilization hours of power generation equipment, end-of-period installed capacity of power sources, newly added industrial capacity, restored industrial capacity after capacity reduction, total imports, total exports, industrial added value, operating income of industrial enterprises, sulfuric acid production, crude steel production, pig iron production, aluminum production, copper production, AC motor production, cement production, and flat glass production.

[0109] After data preprocessing, according to the time-difference correlation analysis results, the leading periods for 11 indicators—non-metallic mineral products industry electricity consumption, total import value, flat glass production, ferrous metal smelting and rolling processing industry electricity consumption, average utilization hours of power generation equipment, total export value, AC motor production, industrial electricity consumption, end-of-period installed capacity of power sources, new industrial capacity, and industrial capacity reduction and recovery—are -11, -11, -10, -10, -10, -6, -6, -4, -3, -3, and -3, respectively, and can be confirmed as [missing data]. Leading indicators reflecting industrial electricity consumption trends; the four indicators of electricity consumption in non-ferrous metal smelting and rolling processing, copper production, cement production, and total exports, whose leading or lagging periods are between -3 and 3 when their time-difference correlation coefficients are at their maximum, are considered consistent indicators; the five indicators of crude steel production, aluminum production, operating income of large-scale industrial enterprises, pig iron production, and sulfuric acid production, whose lagging periods are 3, 4, 4, 6, and 11 when their time-difference correlation coefficients are at their maximum, are lagging indicators reflecting changes in the electricity market, as shown in Table 1: Table 1: Indicator Category Table

[0110] From the results of industrial diffusion index synthesis Figure 2 It can be seen that: from 2011 to 2015, the industrial prosperity index showed cyclical changes, but was generally below 50, indicating a recession; from 2016 to 2018, the industrial prosperity index still showed cyclical changes, but was significantly lower than the level of 2011-2015, indicating a significantly weaker industrial prosperity; from 2019 to 2023, the industrial prosperity index continued to rise overall, with smaller fluctuations and less obvious cyclical changes. In particular, the industrial prosperity index was above 50 in December 2019, December 2020, May, June, July, August, and December 2021, and March 2023, indicating that most indicators in industry were on an upward trend, and industry was in a stage of prosperous development.

[0111] From the results of the industrial synthetic index Figure 3 , Figure 4 It can be seen that the industrial electricity market economy exhibits fluctuations, showing a rapid downward trend starting in 2011 and reaching its trough in 2015. The industrial economy continued to decline, with the index rising again in 2018, reaching a small peak around the first quarter of 2022, before declining again. Comparing leading and coincident indicators, the leading indicator shows a significant lead of approximately four months. The lagging index peaked around the second quarter of 2012, then declined until reaching a trough around August 2020. The lagging index showed some recovery in 2022-2023, but the increase was not significant.

[0112] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that it provides a system for constructing an industrial power prosperity index based on multidimensional data indicators. This system includes an indicator pool generation module, a data processing module, an indicator classification module, and an index generation module. The indicator pool generation module obtains several candidate indicators for characterizing changes in industrial prosperity from multidimensional industrial power data according to preset indicator selection principles, forming a prosperity indicator pool. The data processing module analyzes historical economic data, identifies the peak and trough positions of economic cycles, determines the economic cycle benchmark date as a reference for indicator comparison, and performs preprocessing operations on the historical sequences of each indicator in the prosperity indicator pool to obtain standardized processed sequences for prosperity analysis. The indicator classification module classifies indicators based on the time relationship between the benchmark indicator and other candidate indicators. The system uses ordinal correlation to determine the leading degree of each indicator relative to the economic cycle baseline date, and then classifies the indicators into leading indicators, coincident indicators, and lagging indicators. The index generation module identifies the changing direction of the leading indicator group, coincident indicator group, and lagging indicator group respectively. Based on the proportion of indicators in the expansion state in each group, it generates the leading diffusion index, coincident diffusion index, and lagging diffusion index. Based on the changing characteristics of various indicators, according to the preset weight determination rules, the various indicators are weighted and summarized, and combined with the long-term trend adjustment mechanism, the leading composite index, coincident composite index, and lagging composite index are obtained respectively. The various diffusion indices and various composite indices are used as the basis for economic climate evaluation to form an industrial power prosperity index that represents the stage, operating trend, and changes in the degree of prosperity of the industrial economic cycle.

[0113] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0115] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0116] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented in combination with any of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing an industrial power prosperity index based on multidimensional data indicators, characterized in that: include, According to the preset indicator selection principles, several candidate indicators for characterizing changes in industrial prosperity are obtained from the multidimensional data of industrial power, forming a prosperity indicator pool. Analyze historical economic data to identify the peaks and troughs of economic cycles and determine the benchmark date of the economic cycle for comparison with indicators. Preprocessing is performed on the historical series of each indicator in the economic indicator pool to obtain standardized processed series for economic analysis. Based on the time-series correlation between the benchmark indicator and other candidate indicators, the degree of leading of each indicator relative to the benchmark date of the economic cycle is determined, and the indicators are then classified into leading indicators, coincident indicators and lagging indicators. The changing directions of the leading indicator group, the consistent indicator group, and the lagging indicator group are identified respectively. Based on the proportion of indicators in the expansion state in each group, the leading diffusion index, the consistent diffusion index, and the lagging diffusion index are generated. Based on the changing characteristics of various indicators, the indicators are weighted and aggregated according to the preset weighting rules, and combined with the long-term trend adjustment mechanism to obtain the leading composite index, the consistent composite index and the lagging composite index respectively. By using various diffusion indices and composite indices as the basis for evaluating the economic climate, an industrial power prosperity index is formed that characterizes the stages, operating trends, and changes in the degree of prosperity in the industrial economic cycle.

2. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 1, characterized in that: The acquisition of several candidate indicators for characterizing changes in industrial prosperity includes, Based on the structural characteristics of industrial economic operation, the overall data range for candidate indicator sources is determined from multidimensional data; Within the overall data scope, based on the preset indicator selection principles, various data items are comprehensively evaluated and screened to form a set of candidate indicators; A business climate response characteristic analysis was conducted on the candidate indicator set to examine the performance patterns of each data item in the historical business climate change process. Based on the ability to represent changes in industrial business climate, the candidate indicators used to construct the business climate indicator pool were finally determined.

3. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 2, characterized in that: The determination of the economic cycle benchmark date used as the reference for indicator comparison includes... Select a set of economic indicators that reflect economic fluctuations and are consistent with economic cycle fluctuations, and preliminarily determine the base date of economic fluctuations based on the economic indicators. By comparing the business cycle timeline with the initially determined base date, the final base date for the economic cycle was selected.

4. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 3, characterized in that: The preprocessing operation performed on the historical sequences of each indicator in the economic indicator pool includes... The historical series of each indicator in the economic indicator pool are checked for consistency, missing data is identified, and missing values ​​are filled in using a preset imputation strategy. The completed historical sequence is then normalized. Seasonal decomposition is performed on the normalized historical sequence; Perform trend decomposition on the historical series after seasonal decomposition.

5. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 4, characterized in that: The classification of indicators into leading indicators, consistent indicators, and lagging indicators includes, By comparing the historical change sequences of each candidate indicator in the economic indicator pool with those of the benchmark indicator, the relative change patterns in the time direction are observed, and the time response characteristics of the candidate indicators are preliminarily judged. Based on the initial assessment, by identifying the response order of candidate indicators to the trend changes of benchmark indicators in different time periods, it can be determined whether the trend is reflected before changes in economic activity, whether it changes synchronously with the benchmark indicator, or whether the corresponding trend is shown after changes in the benchmark indicator. Based on the patterns of candidate indicators in terms of time response direction, change rhythm, and the location of characteristic nodes, indicators that show trend changes before the turning point of the benchmark indicator are classified as leading indicators; indicators that show synchronous fluctuation patterns with the benchmark indicator at change nodes are classified as consistent indicators; and indicators that lag behind the benchmark indicator in showing trend changes are classified as lagging indicators.

6. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 5, characterized in that: The generation of the preceding diffusion index, the uniform diffusion index, and the lag diffusion index includes, The number of indicators in the leading indicator group, the consistent indicator group, and the lagging indicator group that were in an expansion state at the same point in time was counted. By comparing the proportion of the expansion state to the total number of indicators in the group, the expansion ratio information was obtained. The statistically obtained expansion ratio information is used as the basis for characterizing the diffusion state, forming the leading diffusion index, the uniform diffusion index, and the lagging diffusion index, respectively.

7. The method for constructing an industrial power prosperity index based on multidimensional data indicators as described in claim 6, characterized in that: The acquisition of the advance synthesis index, the coincident synthesis index, and the lag synthesis index includes, respectively, We extract change features from the leading indicator group, the consistent indicator group, and the lagging indicator group to form a standardized change expression; Based on standardized change expressions, each indicator in the leading indicator group, the consistent indicator group, and the lagging indicator group is weighted according to a preset weight determination rule. Based on the trend of the economic cycle, a trend adjustment operation is performed on the weighted results to form the leading composite index, the coincident composite index, and the lagging composite index.

8. A system for constructing an industrial power prosperity index based on multidimensional data indicators, using the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in any one of claims 1 to 7, characterized in that: It includes an indicator pool generation module, a data processing module, an indicator classification module, and an index generation module; The indicator pool generation module obtains several candidate indicators for characterizing changes in industrial prosperity from multidimensional industrial power data according to preset indicator selection principles, forming a prosperity indicator pool. The data processing module analyzes historical economic data, identifies the peak and trough positions of the economic cycle, determines the economic cycle benchmark date as a reference for indicator comparison, and performs preprocessing operations on the historical sequences of each indicator in the economic indicator pool to obtain standardized processed sequences for economic analysis. The indicator classification module determines the leading degree of each indicator relative to the economic cycle benchmark date based on the time-series correlation between the benchmark indicator and other candidate indicators, and then classifies the indicators into leading indicators, consistent indicators and lagging indicators. The index generation module identifies the changing directions of the leading indicator group, the coincident indicator group, and the lagging indicator group, respectively. Based on the proportion of indicators in the expansion state within each group, it generates the leading diffusion index, the coincident diffusion index, and the lagging diffusion index. Based on the changing characteristics of various indicators, it performs weighted aggregation of various indicators according to preset weight determination rules, and combines a long-term trend adjustment mechanism to obtain the leading composite index, the coincident composite index, and the lagging composite index, respectively. The various diffusion indices and the various composite indices are used as the basis for economic climate evaluation to form an industrial power prosperity index that characterizes the stage, operating trend, and changes in the degree of prosperity of the industrial economic cycle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for constructing an industrial power prosperity index based on multidimensional data indicators as described in any one of claims 1 to 7.

Images